Embodiments of the present disclosure relates generally to video coding techniques, and more particularly, to combination of neural network (NN) based filters for image/video coding.
In nowadays, digital video capabilities are being applied in various aspects of peoples' lives. Multiple types of video compression technologies, such as MPEG-2, MPEG-4, ITU-TH.263, ITU-TH.264/MPEG-4 Part 10 Advanced Video Coding (AVC), ITU-TH.265 high efficiency video coding (HEVC) standard, versatile video coding (VVC) standard, have been proposed for video encoding/decoding. However, coding efficiency of conventional video coding techniques is generally very low, which is undesirable.
Embodiments of the present disclosure provide a solution for video processing.
In a first aspect, a method for video processing is proposed. The method comprises: applying, during a conversion between a video unit of a video and a bitstream of the video unit, a plurality of filters in combination based on a model to the video unit; and performing the conversion based on the applying. The method in accordance with the first aspect of the present disclosure combined the filters adaptively, which can advantageously improve coding efficiency and performance.
In a second aspect, another method for video processing is proposed. The method comprises: determining, during a conversion between a video unit of a video and a bitstream of the video unit, at least one syntax element indicating enabling of combined applying of a plurality of filters; and performing the conversion based on the at least one syntax element. The method in accordance with the second aspect of the present disclosure defines at least one syntax element indicating enabling of combined applying of filters, which advantageously improves coding efficiency and performance.
In a third aspect, an apparatus for processing video data is proposed. The apparatus for processing video data comprises a processor and a non-transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform a method in accordance with the first aspect.
In a fourth aspect, an apparatus for processing video data is proposed. The apparatus for processing video data comprises a processor and a non-transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform a method in accordance with the second aspect.
In a fifth aspect, a non-transitory computer-readable recording medium is proposed. The non-transitory computer-readable recording medium stores a bitstream of a video unit of a video which is generated by a method performed by a video processing apparatus. The method comprises: applying a plurality of filters in combination based on a model to the video unit; and generating the bitstream of the video unit based on the applying.
In a sixth aspect, a method for storing bitstream of a video is proposed. The method comprises: applying a plurality of filters in combination based on a model to a video unit of a video; generating a bitstream of the video unit based on the applying; and storing the bitstream in a non-transitory computer-readable recording medium.
In a seventh aspect, another a non-transitory computer-readable recording medium is proposed. The non-transitory computer-readable recording medium stores a bitstream of a video unit of a video which is generated by a method performed by a video processing apparatus. The method comprises: determining at least one syntax element indicating enabling of combined applying of a plurality of filters; and generating a bitstream of the video unit based on the at least one syntax element.
In an eighth aspect, a method for storing bitstream of a video is proposed. The method comprises: determining at least one syntax element indicating enabling of combined applying of a plurality of filters; generating a bitstream of a video unit of the video based on the at least one syntax element; and storing the bitstream in a non-transitory computer-readable recording medium.
This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Through the following detailed description with reference to the accompanying drawings, the above and other objectives, features, and advantages of example embodiments of the present disclosure will become more apparent. In the example embodiments of the present disclosure, the same reference numerals usually refer to the same components.
Throughout the drawings, the same or similar reference numerals usually refer to the same or similar elements.
Principle of the present disclosure will now be described with reference to some embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. The disclosure described herein can be implemented in various manners other than the ones described below.
In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.
References in the present disclosure to “one embodiment,” “an embodiment,” “an example embodiment,” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an example embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.
It shall be understood that although the terms “first” and “second” etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and/or” includes any and all combinations of one or more of the listed terms.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises”, “comprising”, “has”, “having”, “includes” and/or “including”, when used herein, specify the presence of stated features, elements, and/or components etc., but do not preclude the presence or addition of one or more other features, elements, components and/or combinations thereof.
The video source 112 may include a source such as a video capture device. Examples of the video capture device include, but are not limited to, an interface to receive video data from a video content provider, a computer graphics system for generating video data, and/or a combination thereof.
The video data may comprise one or more pictures. The video encoder 114 encodes the video data from the video source 112 to generate a bitstream. The bitstream may include a sequence of bits that form a coded representation of the video data. The bitstream may include coded pictures and associated data. The coded picture is a coded representation of a picture. The associated data may include sequence parameter sets, picture parameter sets, and other syntax structures. The I/O interface 116 may include a modulator/demodulator and/or a transmitter. The encoded video data may be transmitted directly to destination device 120 via the I/O interface 116 through the network 130A. The encoded video data may also be stored onto a storage medium/server 130B for access by destination device 120.
The destination device 120 may include an I/O interface 126, a video decoder 124, and a display device 122. The I/O interface 126 may include a receiver and/or a modem. The I/O interface 126 may acquire encoded video data from the source device 110 or the storage medium/server 130B. The video decoder 124 may decode the encoded video data. The display device 122 may display the decoded video data to a user. The display device 122 may be integrated with the destination device 120, or may be external to the destination device 120 which is configured to interface with an external display device.
The video encoder 114 and the video decoder 124 may operate according to a video compression standard, such as the High Efficiency Video Coding (HEVC) standard, Versatile Video Coding (VVC) standard and other current and/or further standards.
The video encoder 200 may be configured to implement any or all of the techniques of this disclosure. In the example of
In some embodiments, the video encoder 200 may include a partition unit 201, a predication unit 202 which may include a mode select unit 203, a motion estimation unit 204, a motion compensation unit 205 and an intra-prediction unit 206, a residual generation unit 207, a transform unit 208, a quantization unit 209, an inverse quantization unit 210, an inverse transform unit 211, a reconstruction unit 212, a buffer 213, and an entropy encoding unit 214.
In other examples, the video encoder 200 may include more, fewer, or different functional components. In an example, the predication unit 202 may include an intra block copy (IBC) unit. The IBC unit may perform predication in an IBC mode in which at least one reference picture is a picture where the current video block is located.
Furthermore, although some components, such as the motion estimation unit 204 and the motion compensation unit 205, may be integrated, but are represented in the example of
The partition unit 201 may partition a picture into one or more video blocks. The video encoder 200 and the video decoder 300 may support various video block sizes.
The mode select unit 203 may select one of the coding modes, intra or inter, e.g., based on error results, and provide the resulting intra-coded or inter-coded block to a residual generation unit 207 to generate residual block data and to a reconstruction unit 212 to reconstruct the encoded block for use as a reference picture. In some examples, the mode select unit 203 may select a combination of intra and inter predication (CIIP) mode in which the predication is based on an inter predication signal and an intra predication signal. The mode select unit 203 may also select a resolution for a motion vector (e.g., a sub-pixel or integer pixel precision) for the block in the case of inter-predication.
To perform inter prediction on a current video block, the motion estimation unit 204 may generate motion information for the current video block by comparing one or more reference frames from buffer 213 to the current video block. The motion compensation unit 205 may determine a predicted video block for the current video block based on the motion information and decoded samples of pictures from the buffer 213 other than the picture associated with the current video block.
The motion estimation unit 204 and the motion compensation unit 205 may perform different operations for a current video block, for example, depending on whether the current video block is in an I-slice, a P-slice, or a B-slice. As used herein, an “I-slice” may refer to a portion of a picture composed of macroblocks, all of which are based upon macroblocks within the same picture. Further, as used herein, in some aspects, “P-slices” and “B-slices” may refer to portions of a picture composed of macroblocks that are not dependent on macroblocks in the same picture.
In some examples, the motion estimation unit 204 may perform uni-directional prediction for the current video block, and the motion estimation unit 204 may search reference pictures of list 0 or list 1 for a reference video block for the current video block. The motion estimation unit 204 may then generate a reference index that indicates the reference picture in list 0 or list 1 that contains the reference video block and a motion vector that indicates a spatial displacement between the current video block and the reference video block. The motion estimation unit 204 may output the reference index, a prediction direction indicator, and the motion vector as the motion information of the current video block. The motion compensation unit 205 may generate the predicted video block of the current video block based on the reference video block indicated by the motion information of the current video block.
Alternatively, in other examples, the motion estimation unit 204 may perform bi-directional prediction for the current video block. The motion estimation unit 204 may search the reference pictures in list 0 for a reference video block for the current video block and may also search the reference pictures in list 1 for another reference video block for the current video block. The motion estimation unit 204 may then generate reference indexes that indicate the reference pictures in list 0 and list 1 containing the reference video blocks and motion vectors that indicate spatial displacements between the reference video blocks and the current video block. The motion estimation unit 204 may output the reference indexes and the motion vectors of the current video block as the motion information of the current video block. The motion compensation unit 205 may generate the predicted video block of the current video block based on the reference video blocks indicated by the motion information of the current video block.
In some examples, the motion estimation unit 204 may output a full set of motion information for decoding processing of a decoder. Alternatively, in some embodiments, the motion estimation unit 204 may signal the motion information of the current video block with reference to the motion information of another video block. For example, the motion estimation unit 204 may determine that the motion information of the current video block is sufficiently similar to the motion information of a neighboring video block.
In one example, the motion estimation unit 204 may indicate, in a syntax structure associated with the current video block, a value that indicates to the video decoder 300 that the current video block has the same motion information as the another video block.
In another example, the motion estimation unit 204 may identify, in a syntax structure associated with the current video block, another video block and a motion vector difference (MVD). The motion vector difference indicates a difference between the motion vector of the current video block and the motion vector of the indicated video block. The video decoder 300 may use the motion vector of the indicated video block and the motion vector difference to determine the motion vector of the current video block.
As discussed above, video encoder 200 may predictively signal the motion vector. Two examples of predictive signaling techniques that may be implemented by video encoder 200 include advanced motion vector predication (AMVP) and merge mode signaling.
The intra prediction unit 206 may perform intra prediction on the current video block. When the intra prediction unit 206 performs intra prediction on the current video block, the intra prediction unit 206 may generate prediction data for the current video block based on decoded samples of other video blocks in the same picture. The prediction data for the current video block may include a predicted video block and various syntax elements.
The residual generation unit 207 may generate residual data for the current video block by subtracting (e.g., indicated by the minus sign) the predicted video block (s) of the current video block from the current video block. The residual data of the current video block may include residual video blocks that correspond to different sample components of the samples in the current video block.
In other examples, there may be no residual data for the current video block for the current video block, for example in a skip mode, and the residual generation unit 207 may not perform the subtracting operation.
The transform processing unit 208 may generate one or more transform coefficient video blocks for the current video block by applying one or more transforms to a residual video block associated with the current video block.
After the transform processing unit 208 generates a transform coefficient video block associated with the current video block, the quantization unit 209 may quantize the transform coefficient video block associated with the current video block based on one or more quantization parameter (QP) values associated with the current video block.
The inverse quantization unit 210 and the inverse transform unit 211 may apply inverse quantization and inverse transforms to the transform coefficient video block, respectively, to reconstruct a residual video block from the transform coefficient video block. The reconstruction unit 212 may add the reconstructed residual video block to corresponding samples from one or more predicted video blocks generated by the predication unit 202 to produce a reconstructed video block associated with the current video block for storage in the buffer 213.
After the reconstruction unit 212 reconstructs the video block, loop filtering operation may be performed to reduce video blocking artifacts in the video block.
The entropy encoding unit 214 may receive data from other functional components of the video encoder 200. When the entropy encoding unit 214 receives the data, the entropy encoding unit 214 may perform one or more entropy encoding operations to generate entropy encoded data and output a bitstream that includes the entropy encoded data.
The video decoder 300 may be configured to perform any or all of the techniques of this disclosure. In the example of
In the example of
The entropy decoding unit 301 may retrieve an encoded bitstream. The encoded bitstream may include entropy coded video data (e.g., encoded blocks of video data). The entropy decoding unit 301 may decode the entropy coded video data, and from the entropy decoded video data, the motion compensation unit 302 may determine motion information including motion vectors, motion vector precision, reference picture list indexes, and other motion information. The motion compensation unit 302 may, for example, determine such information by performing the AMVP and merge mode. AMVP is used, including derivation of several most probable candidates based on data from adjacent PBs and the reference picture. Motion information typically includes the horizontal and vertical motion vector displacement values, one or two reference picture indices, and, in the case of prediction regions in B slices, an identification of which reference picture list is associated with each index. As used herein, in some aspects, a “merge mode” may refer to deriving the motion information from spatially or temporally neighboring blocks.
The motion compensation unit 302 may produce motion compensated blocks, possibly performing interpolation based on interpolation filters. Identifiers for interpolation filters to be used with sub-pixel precision may be included in the syntax elements.
The motion compensation unit 302 may use the interpolation filters as used by the video encoder 200 during encoding of the video block to calculate interpolated values for sub-integer pixels of a reference block. The motion compensation unit 302 may determine the interpolation filters used by the video encoder 200 according to the received syntax information and use the interpolation filters to produce predictive blocks.
The motion compensation unit 302 may use at least part of the syntax information to determine sizes of blocks used to encode frame(s) and/or slice(s) of the encoded video sequence, partition information that describes how each macroblock of a picture of the encoded video sequence is partitioned, modes indicating how each partition is encoded, one or more reference frames (and reference frame lists) for each inter-encoded block, and other information to decode the encoded video sequence. As used herein, in some aspects, a “slice” may refer to a data structure that can be decoded independently from other slices of the same picture, in terms of entropy coding, signal prediction, and residual signal reconstruction. A slice can either be an entire picture or a region of a picture.
The intra prediction unit 303 may use intra prediction modes for example received in the bitstream to form a prediction block from spatially adjacent blocks. The inverse quantization unit 304 inverse quantizes, i.e., de-quantizes, the quantized video block coefficients provided in the bitstream and decoded by entropy decoding unit 301. The inverse transform unit 305 applies an inverse transform.
The reconstruction unit 306 may obtain the decoded blocks, e.g., by summing the residual blocks with the corresponding prediction blocks generated by the motion compensation unit 302 or intra-prediction unit 303. If desired, a deblocking filter may also be applied to filter the decoded blocks in order to remove blockiness artifacts. The decoded video blocks are then stored in the buffer 307, which provides reference blocks for subsequent motion compensation/intra predication and also produces decoded video for presentation on a display device.
Some exemplary embodiments of the present disclosure will be described in detailed hereinafter. It should be understood that section headings are used in the present document to facilitate case of understanding and do not limit the embodiments disclosed in a section to only that section. Furthermore, while certain embodiments are described with reference to Versatile Video Coding or other specific video codecs, the disclosed techniques are applicable to other video coding technologies also. Furthermore, while some embodiments describe video coding steps in detail, it will be understood that corresponding steps decoding that undo the coding will be implemented by a decoder. Furthermore, the term video processing encompasses video coding or compression, video decoding or decompression and video transcoding in which video pixels are represented from one compressed format into another compressed format or at a different compressed bitrate.
This disclosure is related to video coding technologies. Specifically, it is related to the loop filter in image/video coding. It may be applied to the existing video coding standard like High-Efficiency Video Coding (HEVC), Versatile Video Coding (VVC), or the standard (e.g., AVS3) to be finalized. It may be also applicable to future video coding standards or video codec or being used as post-processing method which is out of encoding/decoding process.
Video coding standards have evolved primarily through the development of the well-known ITU-T and ISO/IEC standards. The ITU-T produced H.261 and H.263, ISO/IEC produced MPEG-1 and MPEG-4 Visual, and the two organizations jointly produced the H.262/MPEG-2 Video and H.264/MPEG-4 Advanced Video Coding (AVC) and H.265/HEVC standards. Since H.262, the video coding standards are based on the hybrid video coding structure where temporal prediction plus transform coding are utilized. To explore the future video coding technologies beyond HEVC, Joint Video Exploration Team (JVET) was founded by VCEG and MPEG jointly in 2015. Since then, many new methods have been adopted by JVET and put into the reference software named Joint Exploration Model (JEM). In April 2018, the Joint Video Expert Team (JVET) between VCEG (Q6/16) and ISO/IEC JTC1 SC29/WG11 (MPEG) was created to work on the VVC standard targeting at 50% bitrate reduction compared to HEVC. VVC version 1 was finalized in July 2020.
The latest version of VVC draft, i.e., Versatile Video Coding (Draft 10) could be found at: http://phenix.it-sudparis.eu/jvet/doc_end_user/current_document.php?id=10399.
The latest reference software of VVC, named VTM, could be found at: https://vcgit.hhi.fraunhofer.de/jvet/VVCSoftware_VTM/−/tags/VTM-10.0.
Color space, also known as the color model (or color system), is an abstract mathematical model which simply describes the range of colors as tuples of numbers, typically as 3 or 4 values or color components (e.g. RGB). Basically speaking, color space is an elaboration of the coordinate system and sub-space.
For video compression, the most frequently used color spaces are YCbCr and RGB.
YCbCr, Y′CbCr, or Y Pb/Cb Pr/Cr, also written as YCBCR or Y′CBCR, is a family of color spaces used as a part of the color image pipeline in video and digital photography systems. Y′ is the luma component and CB and CR are the blue-difference and red-difference chroma components. Y′ (with prime) is distinguished from Y, which is luminance, meaning that light intensity is nonlinearly encoded based on gamma corrected RGB primaries.
Chroma subsampling is the practice of encoding images by implementing less resolution for chroma information than for luma information, taking advantage of the human visual system's lower acuity for color differences than for luminance.
2.1.1. 4:4:4
Each of the three Y′CbCr components have the same sample rate, thus there is no chroma subsampling. This scheme is sometimes used in high-end film scanners and cinematic post production.
2.1.2. 4:2:2
The two chroma components are sampled at half the sample rate of luma: the horizontal chroma resolution is halved. This reduces the bandwidth of an uncompressed video signal by one-third with little to no visual difference.
2.1.3. 4:2:0
In 4:2:0, the horizontal sampling is doubled compared to 4:1:1, but as the Cb and Cr channels are only sampled on each alternate line in this scheme, the vertical resolution is halved. The data rate is thus the same. Cb and Cr are each subsampled at a factor of 2 both horizontally and vertically. There are three variants of 4:2:0 schemes, having different horizontal and vertical siting.
A picture is divided into one or more tile rows and one or more tile columns. A tile is a sequence of CTUs that covers a rectangular region of a picture.
A tile is divided into one or more bricks, each of which consisting of a number of CTU rows within the tile.
A tile that is not partitioned into multiple bricks is also referred to as a brick. However, a brick that is a true subset of a tile is not referred to as a tile.
A slice either contains a number of tiles of a picture or a number of bricks of a tile.
Two modes of slices are supported, namely the raster-scan slice mode and the rectangular slice mode.
In the raster-scan slice mode, a slice contains a sequence of tiles in a tile raster scan of a picture. In the rectangular slice mode, a slice contains a number of bricks of a picture that collectively form a rectangular region of the picture. The bricks within a rectangular slice are in the order of brick raster scan of the slice.
In VVC, the CTU size, signaled in SPS by the syntax element log 2_ctu_size_minus2, could be as small as 4×4.
log 2_ctu_size_minus2 plus 2 specifies the luma coding tree block size of each CTU.
log 2_min_luma_coding_block_size_minus2 plus 2 specifies the minimum luma coding block size.
The variables CtbLog2SizeY, CtbSizeY, MinCbLog2SizeY, MinCbSizeY, MinTbLog2SizeY, MaxTbLog2Size Y, MinTbSizeY, Max TbSizeY, Pic WidthInCtbs Y, PicHeightInCtbsY, PicSizeInCtbsY, Pic Width InMinCbsY, PicHeightInMinCbsY, PicSizeInMinCbsY, PicSizeInSamples Y, Pic WidthInSamplesC and PicHeightInSamplesC are derived as follows:
Suppose the CTB/LCU size indicated by M×N (typically M is equal to N, as defined in HEVC/VVC), and for a CTB located at picture (or tile or slice or other kinds of types, picture border is taken as an example) border, K×L samples are within picture border where either K<M or L<N.
The input of DB is the reconstructed samples before in-loop filters.
The vertical edges in a picture are filtered first. Then the horizontal edges in a picture are filtered with samples modified by the vertical edge filtering process as input. The vertical and horizontal edges in the CTBs of each CTU are processed separately on a coding unit basis. The vertical edges of the coding blocks in a coding unit are filtered starting with the edge on the left-hand side of the coding blocks proceeding through the edges towards the right-hand side of the coding blocks in their geometrical order. The horizontal edges of the coding blocks in a coding unit are filtered starting with the edge on the top of the coding blocks proceeding through the edges towards the bottom of the coding blocks in their geometrical order.
Filtering is applied to 8×8 block boundaries. In addition, it must be a transform block boundary or a coding subblock boundary (e.g., due to usage of Affine motion prediction, ATMVP). For those which are not such boundaries, filter is disabled.
For a transform block boundary/coding subblock boundary, if it is located in the 8×8 grid, it may be filterd and the setting of bS[xDi][yDj] (where [xDi][yDj] denotes the coordinate) for this edge is defined in Table 1 and Table 2, respectively.
The deblocking decision process is described in this sub-section.
Wider-stronger luma filter is filters are used only if all the Condition1, Condition2 and Condition 3 are TRUE.
The condition 1 is the “large block condition”. This condition detects whether the samples at P-side and Q-side belong to large blocks, which are represented by the variable bSidePisLargeBlk and bSideQisLargeBlk respectively. The bSidePisLargeBlk and bSideQisLargeBlk are defined as follows.
Based on bSidePisLargeBlk and bSideQisLargeBlk, the condition 1 is defined as follows.
Condition1=(bSidePisLargeBlk∥bSidePisLargeBlk)?TRUE: FALSE
Next, if Condition 1 is true, the condition 2 will be further checked. First, the following variables are derived:
Condition2=(d<β)?TRUE: FALSE
If Condition1 and Condition2 are valid, whether any of the blocks uses sub-blocks is further checked:
Finally, if both the Condition 1 and Condition 2 are valid, the proposed deblocking method will check the condition 3 (the large block strong filter condition), which is defined as follows.
In the Condition3 StrongFilterCondition, the following variables are derived:
As in HEVC, StrongFilterCondition=(dpq is less than (β>>2), sp3+sq3 is less than (3*β>>5), and Abs(p0−q0) is less than (5*tC+1)>>1)? TRUE: FALSE.
Bilinear filter is used when samples at either one side of a boundary belong to a large block. A sample belonging to a large block is defined as when the width>=32 for a vertical edge, and when height>=32 for a horizontal edge.
The bilinear filter is listed below.
Block boundary samples pi for i=0 to Sp−1 and qi for j=0 to Sq−1 (pi and qi are the i-th sample within a row for filtering vertical edge, or the i-th sample within a column for filtering horizontal edge) in HEVC deblocking described above) are then replaced by linear interpolation as follows:
where tcPDi and tcPDj term is a position dependent clipping described in Section 2.4.7 and gj, fi Middles,t, Ps and Qs are given below:
The chroma strong filters are used on both sides of the block boundary. Here, the chroma filter is selected when both sides of the chroma edge are greater than or equal to 8 (chroma position), and the following decision with three conditions are satisfied: the first one is for decision of boundary strength as well as large block. The proposed filter can be applied when the block width or height which orthogonally crosses the block edge is equal to or larger than 8 in chroma sample domain. The second and third one is basically the same as for HEVC luma deblocking decision, which are on/off decision and strong filter decision, respectively.
In the first decision, boundary strength (bS) is modified for chroma filtering and the conditions are checked sequentially. If a condition is satisfied, then the remaining conditions with lower priorities are skipped.
Chroma deblocking is performed when bS is equal to 2, or bS is equal to 1 when a large block boundary is detected.
The second and third condition is basically the same as HEVC luma strong filter decision as follows.
In the second condition:
In the third condition StrongFilterCondition is derived as follows:
As in HEVC design, StrongFilterCondition=(dpq is less than (β>>2), sp3+sq3 is less than (β>>3), and Abs (p0−q0) is less than (5*tC+1)>>1).
The following strong deblocking filter for chroma is defined:
The proposed chroma filter performs deblocking on a 4×4 chroma sample grid.
The position dependent clipping tcPD is applied to the output samples of the luma filtering process involving strong and long filters that are modifying 7, 5 and 3 samples at the boundary. Assuming quantization error distribution, it is proposed to increase clipping value for samples which are expected to have higher quantization noise, thus expected to have higher deviation of the reconstructed sample value from the true sample value.
For each P or Q boundary filtered with asymmetrical filter, depending on the result of decision-making process in section 2.4.2, position dependent threshold table is selected from two tables (i.e., Tc7 and Tc3 tabulated below) that are provided to decoder as a side information:
For the P or Q boundaries being filtered with a short symmetrical filter, position dependent threshold of lower magnitude is applied:
Following defining the threshold, filtered p′i and q′i sample values are clipped according to tcP and tcQ clipping values:
where p′i and q′i are filtered sample values, p″i and q″i are output sample value after the clipping and tcPi tcPi are clipping thresholds that are derived from the VVC tc parameter and tcPD and tcQD. The function Clip3 is a clipping function as it is specified in VVC.
To enable parallel friendly deblocking using both long filters and sub-block deblocking the long filters is restricted to modify at most 5 samples on a side that uses sub-block deblocking (AFFINE or ATMVP or DMVR) as shown in the luma control for long filters. Additionally, the sub-block deblocking is adjusted such that that sub-block boundaries on an 8×8 grid that are close to a CU or an implicit TU boundary is restricted to modify at most two samples on each side.
Following applies to sub-block boundaries that not are aligned with the CU boundary.
Where edge equal to 0 corresponds to CU boundary, edge equal to 2 or equal to orthogonalLength−2 corresponds to sub-block boundary 8 samples from a CU boundary etc. Where implicit TU is true if implicit split of TU is used.
The input of SAO is the reconstructed samples after DB. The concept of SAO is to reduce mean sample distortion of a region by first classifying the region samples into multiple categories with a selected classifier, obtaining an offset for each category, and then adding the offset to each sample of the category, where the classifier index and the offsets of the region are coded in the bitstream. In HEVC and VVC, the region (the unit for SAO parameters signaling) is defined to be a CTU.
Two SAO types that can satisfy the requirements of low complexity are adopted in HEVC. Those two types are edge offset (EO) and band offset (BO), which are discussed in further detail below. An index of an SAO type is coded (which is in the range of [0, 2]). For EO, the sample classification is based on comparison between current samples and neighboring samples according to 1-D directional patterns: horizontal, vertical, 135° diagonal, and 45° diagonal.
For a given EO class, each sample inside the CTB is classified into one of five categories. The current sample value, labeled as “c,” is compared with its two neighbors along the selected 1-D pattern. The classification rules for each sample are summarized in Table 1. Categories 1 and 4 are associated with a local valley and a local peak along the selected 1-D pattern, respectively. Categories 2 and 3 are associated with concave and convex corners along the selected 1-D pattern, respectively. If the current sample does not belong to EO categories 1-4, then it is category 0 and SAO is not applied.
The input of DB is the reconstructed samples after DB and SAO. The sample classification and filtering process are based on the reconstructed samples after DB and SAO.
In the JEM, a geometry transformation-based adaptive loop filter (GALF) with block-based filter adaption is applied. For the luma component, one among 25 filters is selected for each 2×2 block, based on the direction and activity of local gradients.
In the JEM, up to three diamond filter shapes (as shown in
Each 2×2 block is categorized into one out of 25 classes. The classification index C is derived based on its directionality D and a quantized value of activity Â, as follows:
To calculate D and Â, gradients of the horizontal, vertical and two diagonal direction are first calculated using 1-D Laplacian:
Indices i and j refer to the coordinates of the upper left sample in the 2×2 block and R(i, j) indicates a reconstructed sample at coordinate (i, j).
Then D maximum and minimum values of the gradients of horizontal and vertical directions are set as:
and the maximum and minimum values of the gradient of two diagonal directions are set as:
To derive the value of the directionality D, these values are compared against each other and with two thresholds t1 and t2:
The activity value A is calculated as:
A is further quantized to the range of 0 to 4, inclusively, and the quantized value is denoted as Â.
For both chroma components in a picture, no classification method is applied, i.e. a single set of ALF coefficients is applied for each chroma component.
Before filtering each 2×2 block, geometric transformations such as rotation or diagonal and vertical flipping are applied to the filter coefficients f(k, l), which is associated with the coordinate (k, l), depending on gradient values calculated for that block. This is equivalent to applying these transformations to the samples in the filter support region. The idea is to make different blocks to which ALF is applied more similar by aligning their directionality.
Three geometric transformations, including diagonal, vertical flip and rotation are introduced:
where K is the size of the filter and 0≤k, l≤K−1 are coefficients coordinates, such that location (0,0) is at the upper left corner and location (K−1, K−1) is at the lower right corner. The transformations are applied to the filter coefficients f (k, l) depending on gradient values calculated for that block. The relationship between the transformation and the four gradients of the four directions are summarized in Table 4.
In the JEM, GALF filter parameters are signalled for the first CTU, i.e., after the slice header and before the SAO parameters of the first CTU. Up to 25 sets of luma filter coefficients could be signalled. To reduce bits overhead, filter coefficients of different classification can be merged. Also, the GALF coefficients of reference pictures are stored and allowed to be reused as GALF coefficients of a current picture. The current picture may choose to use GALF coefficients stored for the reference pictures and bypass the GALF coefficients signalling. In this case, only an index to one of the reference pictures is signalled, and the stored GALF coefficients of the indicated reference picture are inherited for the current picture.
To support GALF temporal prediction, a candidate list of GALF filter sets is maintained. At the beginning of decoding a new sequence, the candidate list is empty. After decoding one picture, the corresponding set of filters may be added to the candidate list. Once the size of the candidate list reaches the maximum allowed value (i.e., 6 in current JEM), a new set of filters overwrites the oldest set in decoding order, and that is, first-in-first-out (FIFO) rule is applied to update the candidate list. To avoid duplications, a set could only be added to the list when the corresponding picture doesn't use GALF temporal prediction. To support temporal scalability, there are multiple candidate lists of filter sets, and each candidate list is associated with a temporal layer. More specifically, each array assigned by temporal layer index (TempIdx) may compose filter sets of previously decoded pictures with equal to lower TempIdx. For example, the k-th array is assigned to be associated with TempIdx equal to k, and it only contains filter sets from pictures with TempIdx smaller than or equal to k. After coding a certain picture, the filter sets associated with the picture will be used to update those arrays associated with equal or higher TempIdx.
Temporal prediction of GALF coefficients is used for inter coded frames to minimize signalling overhead. For intra frames, temporal prediction is not available, and a set of 16 fixed filters is assigned to each class. To indicate the usage of the fixed filter, a flag for each class is signalled and if required, the index of the chosen fixed filter. Even when the fixed filter is selected for a given class, the coefficients of the adaptive filter f(k, l) can still be sent for this class in which case the coefficients of the filter which will be applied to the reconstructed image are sum of both sets of coefficients.
The filtering process of luma component can controlled at CU level. A flag is signalled to indicate whether GALF is applied to the luma component of a CU. For chroma component, whether GALF is applied or not is indicated at picture level only.
At decoder side, when GALF is enabled for a block, each sample R(i, j) within the block is filtered, resulting in sample value R′(i, j) as shown below, where L denotes filter length, fm,n represents filter coefficient, and f(k, l) denotes the decoded filter coefficients.
In VTM4.0, the filtering process of the Adaptive Loop Filter, is performed as follows:
where samples I(x+i, y+j) are input samples, O(x, y) is the filtered output sample (i.e. filter result), and w(i, j) denotes the filter coefficients. In practice, in VTM4.0 it is implemented using integer arithmetic for fixed point precision computations:
where L denotes the filter length, and where w(i, j) are the filter coefficients in fixed point precision.
The current design of GALF in VVC has the following major changes compared to that in JEM:
Equation (11) can be reformulated, without coding efficiency impact, in the following expression:
where w(i, j) are the same filter coefficients as in equation (11) [excepted w(0, 0) which is equal to 1 in equation (13) while it is equal to 1−Σ(i,j)≠(0,0)w(i, j) in equation (11)].
Using this above filter formula of (13), VVC introduces the non-linearity to make ALF more efficient by using a simple clipping function to reduce the impact of neighbor sample values (I(x+i, y+j)) when they are too different with the current sample value (I(x, y)) being filtered.
More specifically, the ALF filter is modified as follows:
where K(d, b)=min (b, max (−b,d)) is the clipping function, and k(i, j) are clipping parameters, which depends on the (i, j) filter coefficient. The encoder performs the optimization to find the best k(i, j).
In some implementation, the clipping parameters k(i, j) are specified for each ALF filter, one clipping value is signaled per filter coefficient. It means that up to 12 clipping values can be signalled in the bitstream per Luma filter and up to 6 clipping values for the Chroma filter.
In order to limit the signaling cost and the encoder complexity, only 4 fixed values which are the same for INTER and INTRA slices are used.
Because the variance of the local differences is often higher for Luma than for Chroma, two different sets for the Luma and Chroma filters are applied. The maximum sample value (here 1024 for 10 bits bit-depth) in each set is also introduced, so that clipping can be disabled if it is not necessary.
The sets of clipping values are provided in the Table 5. The 4 values have been selected by roughly equally splitting, in the logarithmic domain, the full range of the sample values (coded on 10 bits) for Luma, and the range from 4 to 1024 for Chroma.
More precisely, the Luma table of clipping values have been obtained by the following formula:
Similarly, the Chroma tables of clipping values is obtained according to the following formula:
The selected clipping values are coded in the “alf_data” syntax element by using a Golomb encoding scheme corresponding to the index of the clipping value in the above Table 5. This encoding scheme is the same as the encoding scheme for the filter index.
Bilateral image filter is a nonlinear filter that smooths the noise while preserving edge structures. The bilateral filtering is a technique to make the filter weights decrease not only with the distance between the samples but also with increasing difference in intensity. This way, over-smoothing of edges can be ameliorated. A weight is defined as
where Δx and Δy is the distance in the vertical and horizontal and ΔI is the difference in intensity between the samples.
The edge-preserving de-noising bilateral filter adopts a low-pass Gaussian filter for both the domain filter and the range filter. The domain low-pass Gaussian filter gives higher weight to pixels that are spatially close to the center pixel. The range low-pass Gaussian filter gives higher weight to pixels that are similar to the center pixel. Combining the range filter and the domain filter, a bilateral filter at an edge pixel becomes an elongated Gaussian filter that is oriented along the edge and is greatly reduced in gradient direction. This is the reason why the bilateral filter can smooth the noise while preserving edge structures.
The bilateral filter in video coding is proposed as a coding tool for the VVC. The filter acts as a loop filter in parallel with the sample adaptive offset (SAO) filter. Both the bilateral filter and SAO act on the same input samples, each filter produces an offset, and these offsets are then added to the input sample to produce an output sample that, after clipping, goes to the next stage. The spatial filtering strength σd is determined by the block size, with smaller blocks filtered more strongly, and the intensity filtering strength σr is determined by the quantization parameter, with stronger filtering being used for higher QPs. Only the four closest samples are used, so the filtered sample intensity IF can be calculated as
where IC denotes the intensity of the center sample, ΔIA=IA−IC the intensity difference between the center sample and the sample above. ΔIB, ΔIL and ΔIR denote the intensity difference between the center sample and that of the sample below, to the left and to the right respectively.
In deep learning, a convolutional neural network (CNN, or ConvNet) is a class of deep neural networks, most commonly applied to analyzing visual imagery. They have very successful applications in image and video recognition/processing, recommender systems, image classification, medical image analysis, natural language processing.
CNNs are regularized versions of multilayer perceptrons. Multilayer perceptrons usually mean fully connected networks, that is, each neuron in one layer is connected to all neurons in the next layer. The “fully-connectedness” of these networks makes them prone to overfitting data. Typical ways of regularization include adding some form of magnitude measurement of weights to the loss function. CNNs take a different approach towards regularization: they take advantage of the hierarchical pattern in data and assemble more complex patterns using smaller and simpler patterns. Therefore, on the scale of connectedness and complexity, CNNs are on the lower extreme.
CNNs use relatively little pre-processing compared to other image classification/processing algorithms. This means that the network learns the filters that in traditional algorithms were hand-engineered. This independence from prior knowledge and human effort in feature design is a major advantage.
Deep learning-based image/video compression typically has two implications: end-to-end compression purely based on neural networks and traditional frameworks enhanced by neural networks. The first type usually takes an auto-encoder like structure, either achieved by convolutional neural networks or recurrent neural networks. While purely relying on neural networks for image/video compression can avoid any manual optimizations or hand-crafted designs, compression efficiency may be not satisfactory. Therefore, works distributed in the second type take neural networks as an auxiliary, and enhance traditional compression frameworks by replacing or enhancing some modules. In this way, they can inherit the merits of the highly optimized traditional frameworks. For example, a fully connected network for the intra prediction is proposed. In addition to intra prediction, deep learning is also exploited to enhance other modules. For example, the in-loop filters of HEVC with a convolutional neural network is replaced and promising results are achieved. Neural networks are applied to improve the arithmetic coding engine.
In lossy image/video compression, the reconstructed frame is an approximation of the original frame, since the quantization process is not invertible and thus incurs distortion to the reconstructed frame. To alleviate such distortion, a convolutional neural network could be trained to learn the mapping from the distorted frame to the original frame. In practice, training must be performed prior to deploying the CNN-based in-loop filtering.
The purpose of the training processing is to find the optimal value of parameters including weights and bias.
First, a codec (e.g. HM, JEM, VTM, etc.) is used to compress the training dataset to generate the distorted reconstruction frames.
Then the reconstructed frames are fed into the CNN and the cost is calculated using the output of CNN and the groundtruth frames (original frames). Commonly used cost functions include SAD (Sum of Absolution Difference) and MSE (Mean Square Error). Next, the gradient of the cost with respect to each parameter is derived through the back propagation algorithm. With the gradients, the values of the parameters can be updated. The above process repeats until the convergence criteria is met. After completing the training, the derived optimal parameters are saved for use in the inference stage.
During convolution, the filter is moved across the image from left to right, top to bottom, with a one-pixel column change on the horizontal movements, then a one-pixel row change on the vertical movements. The amount of movement between applications of the filter to the input image is referred to as the stride, and it is almost always symmetrical in height and width dimensions. The default stride or strides in two dimensions is (1,1) for the height and the width movement.
During the inference stage, the distorted reconstruction frames are fed into CNN and processed by the CNN model whose parameters are already determined in the training stage. The input samples to the CNN can be reconstructed samples before or after DB, or reconstructed samples before or after SAO, or reconstructed samples before or after ALF.
The prior art design of NN filter is applied to generate the reconstruction. Multiple NN filters are selected directly. Therefore, the NN filters could be not fused adaptively.
The detailed embodiments below should be considered as examples to explain general concepts. These embodiments should not be interpreted in a narrow way. Furthermore, these embodiments can be combined in any manner.
To solve the above problem, it is proposed to combine or fuse the filtered samples generated by the NN filter and/or Non-NN filters. The present disclosure elaborates how to combine the filters, how to utilize or control filtered samples to generate the adaptive reconstruction.
In the disclosure, an independent filter (ID-Filter) means that the filter is not exactly same with other filters and some parts of the filters are different, such as the input of the filter, the structure of the filter, the parameters of filter, the neural network model of the filter. In one example, the design of ID-Filter is unique and different with the design of other filters. In one example, the inputs of ID-Filter are different when filters share the consistent structure or consistent parameters or consistent model of neural network. ID-Filter can be any kind of filters, including filters without neural network (Non-NN filter) and filters with neural network (NN filter). A Non-NN Filter may be one of deblocking filter (DF), sample adaptive offset (SAO), adaptive loop filter (ALF), etc. A NN filter can be any kind of NN filter, such as a convolutional neural network (CNN) filter. In the following discussion, a NN filter may also be referred to as a CNN filter.
In the following discussion, a video unit may be a sequence, a picture, a slice, a tile, a brick, a subpicture, a CTU/CTB, a CTU/CTB row, one or multiple CUs/CBs, one ore multiple CTUs/CTBs, one or multiple VPDU (Virtual Pipeline Data Unit), a sub-region within a picture/slice/tile/brick. A father video unit represents a unit larger than the video unit. Typically, a father unit will contain several video units. E.g., when the video unit is CTU, the father unit could be slice, CTU row, multiple CTUS, etc.
The cross-component SAO is denoted as CCSAO. The cross-component ALF is denoted as CCALF.
The bilateral in-loop filter is denoted as BIF. The Deblocking filter is denoted as DB.
The width and height of a video unit are denoted as W and H, respectively.
In the proposed method, the number of convolutional neural network-based in-loop filtering for slice is three. The number of filters in fusion process is two. The fusion equation is y=a1*x1+ (1−a1)*x2. Firstly, a syntax element is signaled to indicate whether to fuse the NN filters. Secondly, a syntax element is signaled to indicate whether to use the pre-designed parameters or signal the a1 directly when the fusion is enabled. After that, a syntax element is signaled to indicate the value of parameter directly when signal the a1 directly. Moreover, a syntax element is signaled to indicate the index of pre-designed parameters when using the pre-designed parameters.
As used herein, the term “video unit” or “video block” may be a sequence, a picture, a slice, a tile, a brick, a subpicture, a coding tree unit (CTU)/coding tree block (CTB), a CTU/CTB row, one or multiple coding units (CUs)/coding blocks (CBs), one ore multiple CTUs/CTBs, one or multiple Virtual Pipeline Data Unit (VPDU), a sub-region within a picture/slice/tile/brick. As used herein, the term “an independent filter (ID) filter” may refer to a filter is not exactly same with other filters and some parts of the filters are different, such as the input of the filter, the structure of the filter, the parameters of filter, the neural network model of the filter. In one example, the design of ID-Filter is unique and different with the design of other filters. In one example, the inputs of ID-Filter are different when filters share the consistent structure or consistent parameters or consistent model of neural network. ID-Filter can be any kind of filters, including filters without neural network (non-NN filter) and filters with neural network (NN filter). A Non-NN Filter may be one of deblocking filter (DF), sample adaptive offset (SAO), adaptive loop filter (ALF), etc. A NN filter can be any kind of NN filter, such as a convolutional neural network (CNN) filter. In the following discussion, a NN filter may also be referred to as a CNN filter.
As shown in
For example, at least two ID filters may be included in a compatible decoder or encoder. Input information or output information of the plurality of filters may be associated with each other. In some embodiments, the plurality of filters may use same input information. For example, the plurality of filters may be applied in parallel. Alternatively, the plurality of filters may be arranged in series and input information and output information of one filter in the plurality of filters may be used as input information of another filter in the plurality of filters. In some other embodiments, output information of the plurality of filters may be selected for further processing. It is noted that the plurality of filters may include any proper number of filters.
At block 1620, the conversion is performed based on the applying. In some embodiments, the conversion may include encoding the video unit into the bitstream. Alternatively, or in addition, the conversion may include decoding the video unit from the bitstream. Compared with the conventional solution where filters are selected directly, the filters can be adaptively combined for the video unit. In this way, the coding effectiveness and coding efficiency can be improved.
In some embodiments, the applying at block 1610 is adaptive. For example, Whether to and/or how to fuse the ID filters may be adaptive.
In some embodiments, the applying is dependent on statistics of the video unit. Whether to and/or how to fuse the ID filters may be dependent on the statistics of the video unit (e.g., prediction modes, qp, temporal layer, slice type, etc.).
In some embodiments, the model is a linear model or a neural network (NN) model.
In some embodiments, samples output by the plurality of filters are put into a decoded picture buffer, or a final display signal. For example, fused samples may be put into the decoded picture buffer. In another example, fused samples may be the final display signal.
The plurality of filters may be any type of ID filters. In some embodiments, the plurality of filters may include a neural network (NN) filter and/or a non-NN filter. For example, the non-NN filter may include one of: a deblocking filter, a sample adaptive offset (SAO) filter, a bilateral in-loop filter (BIF), an adaptive loop filter (ALF), a cross-component SAO (CCSAO) filter, or a cross-component ALF (CCALF). The NN filter may include a convolutional neural network (CNN) based in-loop filter. In some embodiments, the NN filter and the non-NN filter may be applied according to a predetermined order or an adaptive order.
In some embodiments, samples of the video unit are clipped by applying the plurality of filters. For example, the clipping may be applied to the samples due to the fusion of ID filters.
In some embodiments, the clipping may be dependent on the coding modes and/or coding statistics of the video unit. The coding statistics may comprise at least one of a prediction mode, a quantization parameter (QP), a temporal layer, or a slice type.
Alternatively, the clipping may be dependent on the bit depth of an input signal and/or an internal signal of the plurality of filters.
In some embodiments, the model is a linear model.
In some embodiments, neighboring samples of a current sample of the video unit are involved in the linear model.
In some embodiments, the neighboring samples include samples adjacent and/or non-adjacent to the current sample.
In some embodiments, the linear model may be represented by:
where y represents a fusion sample which is output from the plurality of the filters, xk represents a filtered sample of a filter fk in the plurality of the filters, k represents an index of the filter fk and k is from 1 to K, K represents the total number of the plurality of the filters, and ak, and b are parameters of the linear model.
In some embodiments, the fusion sample or a clipped value of the fusion sample may be a final reconstruction.
In some embodiments, the parameter b may be equal to zero and y=Σak*xk.
In some embodiments, Σak may be equal to a constant value.
In some embodiments, the constant value is 1.0 or 0.0.
In some embodiments, Σak=1 and y=Σak-1*xk-1+(1−Σak-1)*xk+b.
In some embodiments, b=0 and Σak=1 and y=Σak-1*xk-1+(1−Σak-1)*xk.
In some embodiments, K is 1, 2, 3, 4, or 5.
In some embodiments, K=1 and y=a1*x1+b. Alternatively, in some embodiments, K=2 and y=a1*x1+a2*a2+b. As a further alternative, K=3 and y=a1*x1+a2*x2+a3*x3+b.
In some embodiments, K=2 and b=0, such that y=a1*x1+a2*x2.
In some embodiments, K=2 and Σak=1, such that y=a1*x1+(1−a1)*x2+b.
In some embodiments, K=2 and b=0 and Σak=1, such that y=a1*x1+(1−a1)*x2.
In some embodiments, K=3 and b=0, such that y=a1*x1+a2*x2+a3*x3.
In some embodiments, K=3 and Σak=1, such that y=a1*x1+a2*x2+ (1−a1−a2)*x3+b.
In some embodiments, K=3 and b=0 and Σak=1, such that y=a1*x1+a2*x2+ (1−a1−a2)*x3.
In some embodiments, K=2, the plurality of filters may comprise a first filter f1 and a second filter f2, and both the first filter and the second filter are NN filters.
In some embodiments, a model or network structure of the first filter f1 is different with the model of the second filter f2.
In some embodiments, a model or network structure of the first filter f1 is a simplified version of the model of the second filter f2.
In some embodiments, a model of the first filter f is a simplified version of the model of the second filter f2.
In some embodiments, input parameters of the first filter f1 are different with those of the second filter f2.
In some embodiments, a model or network structure of the first filter f1 is same with the model of the second filter f2.
In some embodiments, a model or network structure of the first filter f1 is different with the model of the second filter f2.
In some embodiments, the difference between the first filter f1 and the second filter f2 is training data. The training data may comprise a quality-level indicator. In some embodiments, the quality-level indicator as input is different for the first filter and the second filter.
In some embodiments, the quality-level indicator is quantization parameters (QPs) or lambdas or Constant rate factor (CRF) value or bitrates.
In some embodiments, K=2, the plurality of filters comprise a first filter and a second filter, the first filter is a NN filter, and the second filter is one of the following: a deblocking filter, a sample adaptive offset (SAO) filter, a bilateral in-loop filter (BIF), an adaptive loop filter (ALF), a cross-component SAO (CCSAO) filter, or a cross-component ALF (CCALF).
In some embodiments, K=2, the plurality of filters comprise a first filter and a second filter, the first filter is a NN filter, and the second filter is a group comprising at least one of the following: a deblocking filter, a sample adaptive offset (SAO) filter, a bilateral in-loop filter (BIF), an adaptive loop filter (ALF), a cross-component SAO (CCSAO) filter, or a cross-component ALF (CCALF).
Alternatively, in some embodiments, K=3, the plurality of filters comprise a first filter f1, a second filter f2 and a third filter f3, and all the first, second and third filters are NN filters.
In some embodiments, models or network structure of the first, second and third filters are different with each other.
In some embodiments, a model or a network structure of the first filter and/or the second filter is a simplified version of the model or network structure of the third filter. Alternatively, a model or a network structure of the first filter and/or the third filter is a simplified version of the model or network structure of the second filter. As a further alternative, a model or network structure of the second filter and/or the third filter is a simplified version of the model or network structure of the first filter.
In some embodiments, the input parameters of the first filter, the second filter and/or the third filter are different with each other. In some embodiments, a model or a network structure of the first filter, the second filter and/or the third filter is the same or different with each other. The difference between the first filter, the second filter and/or the third filter may be training data. For example, the training data may comprise a quality-level indicator.
In some implementations, the quality-level indicator as input may be different for the first filter, the second filter and/or the third filter. The quality-level indicator may be quantization parameters (QPs) or lambdas or Constant rate factor (CRF) value or bitrates.
In some embodiments, wherein K=3, the plurality of filters may comprise a first filter, a second filter and a third filter, each of them is one of the following: a NN filter, a deblocking filter, a sample adaptive offset (SAO) filter, a bilateral in-loop filter (BIF), an adaptive loop filter (ALF), a cross-component SAO (CCSAO) filter, or a cross-component ALF (CCALF).
In some embodiments, K=3, the plurality of filters comprise a first filter, a second filter and a third filter, each of them is one of a NN filter, or a group comprising at least one of the following: a deblocking filter, a sample adaptive offset (SAO) filter, a bilateral in-loop filter (BIF), an adaptive loop filter (ALF), a cross-component SAO (CCSAO) filter, or a cross-component ALF (CCALF).
In some embodiments, at least one of K, ak or b is an adaptive or constant value, or is indicated by one or more indicators.
In some embodiments, at least one of K, ak or b is dependent on coding modes and/or statistics of the video unit.
In some embodiments, at least one of K, ak or b is a predetermined value. That is, K and/or ak and/or b may be pre-designed values.
In some embodiments, ak may be 1.0, ⅞, ¾, 0.75, ½, 0.5, ¼, 0.25, or 0.0.
In some embodiments, at least one of K, ak or b is selected from predetermined values, constant values and/or indicators.
In some embodiments, a non-linear model is applied to filtered samples with the plurality of filters and/or neighboring samples of a current sample of the video unit.
In some embodiments, the neighboring samples include samples adjacent and/or non-adjacent to the current sample.
In some embodiments, whether to and/or how to construct one or more candidate lists of the plurality of filters are dependent on coding statistics of the video unit. The coding statistics may comprise at least one of a prediction mode, a quantization parameter (QP), or a slice type.
In some embodiments, the number NC of candidate lists may be a constant number. For example, the number NC of candidate lists may be 0, 1, 2, 3, or 4. In another example, the number NC of candidate lists may be a positive integer.
In some embodiments, the number NC of candidate lists may be dependent on the number Nf of NN filters in the plurality of filters.
In some embodiments, the number of candidate lists is equal to the number of NN filters. That is, NC may be equal to Nf.
In some embodiments, the number of candidate lists is equal to a sum of the number of NN filters and a predetermined value. That is, NC may be equal to Nf+M, where M is the predetermined value.
In some embodiments, the predetermined value M may be −1, 0, 1, 2, 3, or 4. In some embodiments, the predetermined value M may be a positive integer.
In some embodiments, the number NC of candidate lists is two times of the number of NN filters. That is, NC may be equal to 2{circumflex over ( )}Nf.
In some embodiments, the number NC of candidate lists is indicated by one or more indicators.
In some embodiments, a fusion candidate of the plurality of filters comprises a first number of filters. The first number Nk may be 0, 1, 2, 3, or 4. Alternatively, the first number Nk may be dependent on the number of NN filters in the plurality of filters, for example, the first number Nk may be equal to the number of NN filters in the plurality of filters. As a further alternative, the first number may be equal to the total number of the plurality of the filters. For example, Nk may be equal to K disclosed above in the linear model.
In some embodiments, the plurality of filters comprise a first NN filter fA, a second NN filter fB and a third NN filter fC.
In some embodiments, a first fusion candidate mode is a fusion of a function F (fA) of the first NN filter and a function F (fB) of the second NN filter.
In some embodiments, a second fusion candidate mode is a fusion of a function F (fB) of the second NN filter and a function F (fC) of the third NN filter.
In some embodiments, a third fusion candidate mode is a fusion of a function F (fC) of the third NN filter and a function F (fA) of the first NN filter.
In some embodiments, a function of a target NN filter is the same with the target filter, wherein the target filter is one of the first NN filter, the second NN filter, or the third NN filter.
In some embodiments, a function of a target NN filter is a simplified version of the target filter, wherein the target filter is one of the first NN filter, the second NN filter, or the third NN filter.
In some embodiments, a function of a target NN filter is dependent on the target filter, wherein the target filter is one of the first NN filter, the second NN filter, or the third NN filter.
In some embodiments, a function of a target NN filter is adaptive for different implementations of the target filter, wherein the target filter is one of the first NN filter, the second NN filter, or the third NN filter.
In one example, F (fX) disclosed above may be same with fX. In one example, F (fX) disclosed above may be a simplified version of fX. In one example, F (fX) disclosed above may be dependent on the fX. In one example, F (fX) disclosed above may be adaptive for different fX.
In some embodiments, an order of fusion candidates of the plurality of filters is adaptive. That is, the candidate order may be adaptive.
In some embodiments, an order of fusion candidates of the plurality of filters is dependent on coding statistics of the video unit. The candidate order may be dependent on the coding statistics of the video unit (e.g. prediction modes, qp, slice type, etc.).
In some embodiments, an order of fusion candidates of the plurality of filters is pre-designed.
In some embodiments, one or each of fusion candidates only comprises NN filters.
In some embodiments, one or each of fusion candidates comprises NN filters and Non-NN filters.
In some embodiments, a Non-NN filter is one of the following, or is a group comprising at least one of the following: a deblocking filter, a sample adaptive offset (SAO) filter, a bilateral in-loop filter (BIF), an adaptive loop filter (ALF), a cross-component SAO (CCSAO) filter, or a cross-component ALF (CCALF). In one example, Non-NN filter may be DB or SAO or BIF or CCSAO or CCALF or ALF. In another example, Non-NN filter may be a group of DB and/or SAO and/or BIF and/or CCSAO and/or CCALF and/or ALF.
Whether to and/or how to utilize the fusion result of ID filters may be dependent on the coding modes/statistics of the video unit (e.g., prediction modes, qp, temporal layer, slice type, etc.). In some embodiments, whether to and/or a way to utilize a fusion result of the plurality of filters is dependent on at least one of: a coding mode of the video unit, a coding statistic of the video unit, a prediction mode, QP, a temporal layer, a slice type, a quantization step, a block size of the video unit, color components, or a signal in the bitstream.
In some embodiments, the signal is in at least one of: a sequence, a picture, a slice, a tile, a brick, a subpicture, a coding tree unit (CTU), a coding tree block (CTB), a CTU row, a CTB row, a coding unit (CU), a coding block (CB), a plurality of CUs, or a plurality of CBs.
In some embodiments, the number of filters in the plurality of filters is an integer number.
In some embodiments, the number of filters may be 0, 1, 2, 3, 4, 5, or 6. Alternatively, the number of filters may be depending on a statistic of the video unit. In some embodiments, the statistic may comprise at least one of: a prediction mode, QP, a temporal layer, or a slice type.
In some embodiments, usage of the plurality of filters may be dependent on an indicator in at least one of: a sequence, a picture, a slice, a tile, a brick, a subpicture, a coding tree unit (CTU), a coding tree block (CTB), a CTU row, a CTB row, a coding unit (CU), a coding block (CB), a plurality of CUs, or a plurality of CBs.
In some embodiments, the plurality of filters are a group of filters.
In some embodiments, clipping is applied to samples due to the fusion result of the plurality of filters. In some alternative embodiments, the clipping may be dependent on coding modes and/or coding statistics of the video unit. The coding statistics may comprise at least one of a prediction mode, a quantization parameter (QP), a temporal layer, or a slice type. Alternatively, in some embodiments, the clipping may be dependent on a bit depth of an input signal and/or internal signal of the plurality of filters.
In some embodiments, the fusion result is put into a decoded picture buffer.
In some embodiments, the fusion result is a final display signal.
In some embodiments, a model of a first filter in the plurality of filters is a simplified version of a model of a second filter in the plurality of filters.
In some embodiments, the plurality of filters are NN filters. Depth of models of the NN filters may be different. Feature maps of the models of the NN filters may be different. The number of residual blocks of the models of the NN filters may be different. Or, a convolution kernel of the models of the NN filters may be different.
In some embodiments, models of the NN filter used in the applying have a shallower depth. The models of the NN filters may have less feature maps.
In some embodiments, the number of residual blocks of models of the NN filters used in the applying are less. Or, the number of residual blocks may be 1, 2, 3, 4, 5, or 6.
In some embodiments, a simplified model and a normal model of the plurality of filters are used in the applying.
According to further embodiments of the present disclosure, a non-transitory computer-readable recording medium is provided. The non-transitory computer-readable recording medium stores a bitstream of a video which is generated by a method performed by a video processing apparatus. The method comprises: applying a plurality of filters in combination based on a model to the video unit; and generating the bitstream of the video unit based on the applying.
According to still further embodiments of the present disclosure, a method for storing bitstream of a video is provided. The method comprises: applying a plurality of filters in combination based on a model to a video unit of a video; generating a bitstream of the video unit based on the applying; and storing the bitstream in a non-transitory computer-readable recording medium.
As shown in
At block 1720, the conversion is performed based on the at least one syntax element. In some embodiments, the conversion may include encoding the video unit into the bitstream. Alternatively, or in addition, the conversion may include decoding the video unit from the bitstream.
Compared with the conventional solution, the proposed solution controls the usage/enabling of fusion of filters adding one or more syntax elements, for example, at different levels, which advantageously improves coding efficiency and performance.
In some embodiments, the at least one syntax element may be indicated at a first level. In some embodiments, the first level may be a sequence level. The at least one syntax element may be comprised in a sequence parameter set (SPS) or sequence header.
In some embodiments, the at least one syntax element comprises a first flag indicating whether the combined applying is enabled.
In some embodiments, the combined applying is enabled if the first flag is true or 1, or the combined applying is not enabled if the flag is false or 0.
In some embodiments, the at least one syntax element at the first level may comprise a syntax element indicating the number of fusion modes which are potentially used in the combined applying of the plurality of filters. The at least one syntax element may be signaled only if the combined applying is enabled.
In some embodiments, the at least one syntax element at the first level may comprise a syntax element indicating whether the combined applying is to be used in the first level.
In some embodiments, the at least one syntax element at the first level may comprise a syntax element indicating whether the combined applying can be adaptively/non-adaptive used or selected in a second level.
In some embodiments, the at least one syntax element is indicated at a second level different from a first level. The second level may be a picture level or a slice level.
In some embodiments, the second level is the picture level and the at least one syntax element is comprised in a picture header (PH) or picture parameter set (PPS).
In some embodiments, the second level is the slice level and the at least one syntax element is comprised in a slice header (SH).
In some embodiments, the at least one syntax element at the second level is conditionally indicated in a bitstream.
In some embodiments, whether the at least one syntax element is indicated is based on one or more syntax elements indicated at the first level.
In some embodiments, the at least one syntax element indicated at the second level comprises a first flag indicating whether the combined applying is enabled in the second level.
In some embodiments, the at least one syntax element indicated at the second level comprises a syntax element indicating the number of fusion modes which can be used in the second level.
In some embodiments, the number of fusion modes is a default value. The default value may be 0, 1, 2, or 3.
In some embodiments, the at least one syntax element is not indicated in a bitstream. In some embodiments, the at least one syntax element indicated at the second level may comprise a syntax element indicating whether the combined applying is to be used at the second level.
In some embodiments, the at least one syntax element indicated at the second level comprises a syntax element indicating an index of a fusion candidate of the plurality of filters.
In some embodiments, the index of the fusion candidate is the same as an indicator of the index of a selecting filter.
In some embodiments, whether the at least one syntax element is indicated is based on syntax elements indicating the number of fusion modes.
In some embodiments, the at least one syntax element indicated at the second level comprises a syntax element indicating fusion parameters.
In some embodiments, the at least one syntax element indicates the number of filters used in one fusion mode.
In some embodiments, the combined applying of the plurality of filters is based on a linear mode represented by:
where y represents a fusion sample which is output from the plurality of the filters, xk represents a filtered sample of a filter fk in the plurality of the filters, k represents an index of the filter fk and k is from 1 to K, K represents the total number of the plurality of the filters, and ak, and b are parameters of the linear model. The at least one syntax element may indicate whether the parameter ak is indicated by a direct syntax element or an indirect syntax element, or indicate the parameter ak, or indicate a function of the parameter ak, or indicate an index of the parameter ak, or indicate offset parameter b, or indicate an index of pre-designed values for ak.
In some embodiments, ak is equal to a value of the at least one syntax element multiply/divided by a factor T.
In some embodiments, the factor T is equal to 2{circumflex over ( )}W, 2{circumflex over ( )}W represents 2 to the power of W, where W is a positive integer, or W is one of 0, 2, 4, 6, 8, 10, 12, 14, or 16. In some embodiments, T may be a positive integer.
In some embodiments, whether the at least one syntax element is to be indicated in the bitstream is dependent on a previous indirect syntax element.
In some embodiments, syntax elements for fusion candidates of the plurality of filters are different.
In some embodiments, the at least one syntax element at a second level comprises a syntax element indicating whether the combined applying can be adaptively/non-adaptive used or selected at a third level.
In some embodiments, the at least one syntax element is indicated at a third level, the third level being different from a first level or a second level.
In some embodiments, the third level corresponds to one of a patch, a coding tree unit (CTU), a coding tree block (CTB), a block, a subpicture, a tile, a slice, or a region containing multiple samples.
In some embodiments, the at least one syntax element at the third level is conditionally indicated in a bitstream.
In some embodiments, whether the at least one syntax element is indicated is based on one or more syntax elements indicated at the first level or the second level.
In some embodiments, the at least one syntax element indicated at the third level comprises a first flag indicating whether the combined applying is enabled in the third level.
In some embodiments, the at least one syntax element indicated at the third level comprises a syntax element indicating whether the combined applying is to be used in the third level.
In some embodiments, the at least one syntax element indicated at the third level comprises a syntax element indicating an index of a fusion candidate of the plurality of filters.
In some embodiments, the index of the fusion candidate is the same as an indicator of the index of a selecting filter.
In some embodiments, whether the at least one syntax element is indicated is based on syntax elements indicating the number of fusion modes in the second level.
In some embodiments, whether the at least one syntax element is indicated is based on syntax elements indicating the number of indices of fusion candidates in the second level.
In some embodiments, the at least one syntax element indicated at the third level comprises a syntax element indicating fusion parameters.
In some embodiments, the at least one syntax element indicating whether to use the fusion parameters in the second level or the third level.
In some embodiments, one of the at least one syntax element at the third level is conditionally signaled.
In some embodiments, whether the at least one syntax element at the third level is indicated is based on a syntax element indicating whether to use the fusion parameters in the second level or in the third level.
In some embodiments, the at least one syntax element indicates the number of filters used in one fusion mode.
In some embodiments, the combined applying of the plurality of filters is based on a linear mode represented by:
where y represents a fusion sample which is output from the plurality of the filters, xk represents a filtered sample of a filter fk in the plurality of the filters, k represents an index of the filter fk and k is from 1 to K, K represents the total number of the plurality of the filters, and ak, and b are parameters of the linear model. The at least one syntax element may indicate whether the parameter ak is indicated by a direct syntax element or an indirect syntax element, or indicate the parameter ak, or indicate a function of the parameter ak, or indicate an index of the parameter ak, or indicate offset parameter b, or indicates an index of pre-designed values for ak.
In some embodiments, ak is equal to a value of the at least one syntax element multiply/divided by a factor T.
In some embodiments, the factor T is equal to 2{circumflex over ( )}W, 2{circumflex over ( )}W represents 2 to the power of W, wherein W is a positive integer, or W is one of 0, 2, 4, 6, 8, 10, 12, 14, or 16. In some embodiments, T is a positive integer.
In some embodiments, whether the at least one syntax element is to be indicated in the bitstream is dependent on a previous indirect syntax element.
In some embodiments, syntax elements for fusion candidates of the plurality of filters are different.
In some embodiments, one of the at least one syntax element is set to a default value.
In some embodiments, the at least one syntax element is not indicated in a bitstream.
In some embodiments, a first syntax element of the at least one syntax element is set to a default value only if the first syntax element is not indicated in the bitstream. In some embodiments, the default value may be −1, 0, 1, 2, 3, or 4.
In some embodiments, the at least one syntax element may be indicated by context coding or bypass coding.
In some embodiments, the at least one syntax element is binarized using one of the following: fixed length coding, or unary coding, or truncated unary coding, or signed unary coding, or signed truncated unary coding, or truncated binary coding, or k-th exponential golomb coding. In some embodiments, k is a positive integer, or wherein k is equal to 0, 1, 2, 3, 4, 5, or 6.
In some embodiments, the at least one syntax element is indicated individually for different color components. The syntax elements disclosed above may be signaled individually for different color components.
In some embodiments, the at least one syntax element is indicated only for a first set of color components. The first set of color components may comprise Y or Cb or Cr color components.
In some embodiments, the first set of color components comprise R or G or B color components.
In some embodiments, information of components other than the first set of color components is indicated by one or more syntax elements of a second set of color components.
In some embodiments, the at least one syntax element is indicated for all available color components. In some embodiments, the at least one syntax element is indicated for Luma color components. In some embodiments, the at least one syntax element is indicated for Chroma color components.
In some embodiments, Cb and Cr color components share the same syntax elements.
In some embodiments, the at least one syntax element is indicated for Y and/or Cb and/or Cr color components.
In some embodiments, the at least one syntax element is indicated for R and/or G and/or B color components.
In some embodiments, a Luma color component indicates a Y component.
In some embodiments, a Chroma color component indicates a Cb or Cr component.
In some embodiments, the at least one syntax element is indexed by the color components.
In some embodiments, the plurality of filters is applied in combination to a NN based coding method.
In some embodiments, at least one of the plurality of filters is replaced by an intra prediction method.
In some embodiments, the intra prediction method is a NN based method or a non-NN based method.
In some embodiments, at least one of the plurality of filters is replaced by an inter prediction method.
In some embodiments, the inter prediction method is a NN based method or a non-NN based method.
In some embodiments, the plurality of filters may be applied to an unified NN filtering method. The plurality of filters may be applied to a non-unified NN filtering method.
In some embodiments, the plurality of filters are applied to at least one of: a NN based intra method or a NN based inter method.
In some embodiments, the plurality of filters are applied to at least one of: a non-NN based intra method or a non-NN based inter method.
In some embodiments, one filter of the plurality of filters is a NN based intra or inter method, and another filter of the plurality of filters is a non-NN based intra or inter method.
In some embodiments, the one filter and the other filter of the plurality of filters are combined.
In some embodiments, the conversion includes encoding the video unit into the bitstream.
In some embodiments, the conversion includes decoding the video unit from the bitstream.
According to further embodiments of the present disclosure, a non-transitory computer-readable recording medium is provided. The non-transitory computer-readable recording medium stores a bitstream of a video which is generated by a method performed by a video processing apparatus. The method comprises: determining at least one syntax element indicating enabling of combined applying of a plurality of filters; and generating a bitstream of the video unit based on the at least one syntax element.
According to still further embodiments of the present disclosure, a method for storing bitstream of a video is provided. The method comprises: determining at least one syntax element indicating enabling of combined applying of a plurality of filters; generating a bitstream of a video unit of the video based on the at least one syntax element; and storing the bitstream in a non-transitory computer-readable recording medium.
Implementations of the present disclosure can be described in view of the following clauses, the features of which can be combined in any reasonable manner.
Clause 1. A method of video processing, comprising: applying, during a conversion between a video unit of a video and a bitstream of the video unit, a plurality of filters in combination based on a model to the video unit; and performing the conversion based on the applying.
Clause 2. The method of clause 1, wherein the applying is adaptive.
Clause 3. The method of clause 1, wherein the applying is dependent on statistics of the video unit.
Clause 4. The method of clause 1, wherein the model is a linear model or a neural network (NN) model.
Clause 5. The method of clause 1, wherein samples output by the plurality of filters are put into a decoded picture buffer, or a final display signal.
Clause 6. The method of clause 1, wherein the plurality of filters comprise a NN filter and/or a non-NN filter.
Clause 7. The method of clause 1, wherein samples of the video unit are clipped by applying the plurality of filters.
Clause 8. The method of clause 7, wherein the clipping is dependent on the coding modes and/or coding statistics of the video unit.
Clause 9. The method of clause 3 or 8, wherein the coding statistics comprise at least one of a prediction mode, a quantization parameter (QP), a temporal layer, or a slice type.
Clause 10. The method of clause 7, wherein the clipping is dependent on the bit depth of an input signal and/or an internal signal of the plurality of filters.
Clause 11. The method of clause 1, wherein the model is a linear model.
Clause 12. The method of clause 11, wherein neighboring samples of a current sample of the video unit are involved in the linear model.
Clause 13. The method of clause 12, wherein the neighboring samples include samples adjacent and/or non-adjacent to the current sample.
Clause 14. The method of clause 11, wherein the linear model is represented by:
wherein y represents a fusion sample which is output from the plurality of the filters, xk represents a filtered sample of a filter fk in the plurality of the filters, k represents an index of the filter fk and k is from 1 to K, K represents the total number of the plurality of the filters, and ak, and b are parameters of the linear model.
Clause 15. The method of clause 14, wherein the fusion sample or a clipped value of the fusion sample is a final reconstruction.
Clause 16. The method of clause 14, wherein b is equal to zero and y=Σak*xk.
Clause 17. The method of clause 16, wherein Σak is equal to a constant value.
Clause 18. The method of clause 16, wherein Σak=1 and y=Σak-1*xk-1+ (1−Σak-1)*xk+b.
Clause 19. The method of clause 14, wherein b=0 and Σak=1 and y=Σak-1*xk-1+ (1−Σak-1)*xk.
Clause 20. The method of clause 14, wherein K is 1, 2, 3, 4, or 5.
Clause 21. The method of clause 14, wherein K=1 and y=a1*x1+b, or
Clause 22. The method of clause 14, wherein K=2 and b=0, such that y=a1*x1+a2*x2.
Clause 23. The method of clause 14, wherein K=2 and Σak=1, such that y=a1*x1+ (1−a1)*x2+b.
Clause 24. The method of clause 14, wherein K=2 and b=0 and Σak=1, such that y=a1*x1+ (1−a1)*x2.
Clause 25. The method of clause 14, wherein K=3 and b=0, such that y=a*x1+a2*x2+a3*x3.
Clause 26. The method of clause 14, wherein K=3 and Σak=1, such that y=a1*x1+a2*x2+ (1−a1−a2)*x3+b.
Clause 27. The method of clause 14, wherein K=3 and b=0 and Σak=1, such that y=a1*x1+a2*x2+ (1−a1-a2)*x3.
Clause 28. The method of clause 14, wherein K=2, the plurality of filters comprise a first filter and a second filter, and both the first filter and the second filter are NN filters.
Clause 29. The method of clause 28, wherein a model or network structure of the first filter is different with the model of the second filter.
Clause 30. The method of clause 28, wherein a model or network structure of the first filter is a simplified version of the model of the second filter.
Clause 31. The method of clause 28, wherein a model of the first filter is a simplified version of the model of the second filter.
Clause 32. The method of clause 28, wherein input parameters of the first filter are different with those of the second filter.
Clause 33. The method of clause 32, wherein a model or network structure of the first filter is same with the model of the second filter.
Clause 34. The method of clause 32, wherein a model or network structure of the first filter is different with the model of the second filter.
Clause 35. The method of clause 32, wherein the difference between the first filter and the second filter is training data.
Clause 36. The method of clause 35, wherein the training data comprises a quality-level indicator.
Clause 37. The method of clause 36, wherein the quality-level indicator as input is different for the first filter and the second filter.
Clause 38. The method of clause 36, wherein the quality-level indicator is quantization parameters (QPs) or lambdas or Constant rate factor (CRF) value or bitrates.
Clause 39. The method of clause 14, wherein K=2, the plurality of filters comprise a first filter and a second filter, the first filter is a NN filter, and the second filter is one of the following: a deblocking filter, a sample adaptive offset (SAO) filter, a bilateral in-loop filter (BIF), an adaptive loop filter (ALF), a cross-component SAO (CCSAO) filter, or a cross-component ALF (CCALF).
Clause 40. The method of clause 14, wherein K=2, the plurality of filters comprise a first filter and a second filter, the first filter is a NN filter, and the second filter is a group comprising at least one of the following: a deblocking filter, a sample adaptive offset (SAO) filter, a bilateral in-loop filter (BIF), an adaptive loop filter (ALF), a cross-component SAO (CCSAO) filter, or a cross-component ALF (CCALF).
Clause 41. The method of clause 14, wherein K=3, the plurality of filters comprise a first filter, a second filter and a third filter, and all the first, second and third filters are NN filters.
Clause 42. The method of clause 41, wherein models or network structure of the first, second and third filters are different with each other.
Clause 43. The method of clause 41, wherein a model or a network structure of the first filter and/or the second filter is a simplified version of the model or network structure of the third filter, or wherein a model or a network structure of the first filter and/or the third filter is a simplified version of the model or network structure of the second filter, or wherein model or network structure of the second filter and/or the third filter is a simplified version of the model or network structure of the first filter.
Clause 44. The method of clause 41, wherein the input parameters of the first filter, the second filter and/or the third filter are different with each other.
Clause 45. The method of clause 44, wherein a model or a network structure of the first filter, the second filter and/or the third filter is the same or different with each other.
Clause 46. The method of clause 45, wherein the difference between the first filter, the second filter and/or the third filter is training data.
Clause 47. The method of clause 46, wherein the training data comprises a quality-level indicator.
Clause 48. The method of clause 47, wherein the quality-level indicator as input is different for the first filter, the second filter and/or the third filter.
Clause 49. The method of clause 47, wherein the quality-level indicator is quantization parameters (QPs) or lambdas or Constant rate factor (CRF) value or bitrates.
Clause 50. The method of clause 14, wherein K=3, the plurality of filters comprise a first filter, a second filter and a third filter, each of them is one of the following: a NN filter, a deblocking filter, a sample adaptive offset (SAO) filter, a bilateral in-loop filter (BIF), an adaptive loop filter (ALF), a cross-component SAO (CCSAO) filter, or a cross-component ALF (CCALF).
Clause 51. The method of clause 14, wherein K=3, the plurality of filters comprise a first filter, a second filter and a third filter, each of them is one of a NN filter, or a group comprising at least one of the following: a deblocking filter, a sample adaptive offset (SAO) filter, a bilateral in-loop filter (BIF), an adaptive loop filter (ALF), a cross-component SAO (CCSAO) filter, or a cross-component ALF (CCALF).
Clause 52. The method of clause 14, wherein at least one of K, ak or b is an adaptive or constant value, or is indicated by one or more indicators.
Clause 53. The method of clause 14, wherein at least one of K, ak or b is dependent on coding modes and/or statistics of the video unit.
Clause 54. The method of clause 14, wherein at least one of K, ak or b is a predetermined value.
Clause 55. The method of clause 54, wherein ak is one of 1.0, ⅞, ¾, 0.75, ½, 0.5, ¼, 0.25, or 0.0.
Clause 56. The method of clause 14, wherein at least one of K, ak or b is selected from predetermined values, constant values and/or indicators.
Clause 57. The method of clause 1, wherein a non-linear model is applied to filtered samples with the plurality of filters and/or neighboring samples of a current sample of the video unit.
Clause 58. The method of clause 57, wherein the neighboring samples include samples adjacent and/or non-adjacent to the current sample.
Clause 59. The method of clause 1, wherein whether to and/or how to construct one or more candidate lists of the plurality of filters are dependent on coding statistics of the video unit.
Clause 60. The method of clause 59, wherein the coding statistics comprise at least one of a prediction mode, a quantization parameter (QP), or a slice type.
Clause 61. The method of clause 59, wherein the number of candidate lists is a constant number.
Clause 62. The method of clause 61, wherein the number of candidate lists is 0, 1, 2, 3, or 4, or wherein the number of candidate lists is a positive integer.
Clause 63. The method of clause 59, wherein the number of candidate lists is dependent on the number of NN filters in the plurality of filters.
Clause 64. The method of clause 63, wherein the number of candidate lists is equal to the number of NN filters.
Clause 65. The method of clause 63, wherein the number of candidate lists is equal to a sum of the number of NN filters and a predetermined value.
Clause 66. The method of clause 65, wherein the predetermined value is −1, 0, 1, 2, 3, or 4, or wherein the predetermined value is a positive integer.
Clause 67. The method of clause 63, wherein the number of candidate lists is two times of the number of NN filters.
Clause 68. The method of clause 59, wherein the number of candidate lists is indicated by one or more indicators.
Clause 69. The method of clause 59, wherein a fusion candidate of the plurality of filters comprises a first number of filters.
Clause 70. The method of clause 69, wherein the first number is one of 0, 1, 2, 3, or 4.
Clause 71. The method of clause 69, wherein the first number is dependent on the number of NN filters in the plurality of filters.
Clause 72. The method of clause 71, wherein the first number is equal to the number of NN filters in the plurality of filters.
Clause 73. The method of clause 69, wherein the first number is equal to the total number of the plurality of the filters.
Clause 74. The method of clause 59, wherein the plurality of filters comprise a first NN filter, a second NN filter and a third NN filter.
Clause 75. The method of clause 74, wherein a first fusion candidate mode is a fusion of a function of the first NN filter and a function of the second NN filter.
Clause 76. The method of clause 74, wherein a second fusion candidate mode is a fusion of a function of the second NN filter and a function of the third NN filter.
Clause 77. The method of clause 74, wherein a third fusion candidate mode is a fusion of a function of the third NN filter and a function of the first NN filter.
Clause 78. The method of any of clauses 75-77, wherein a function of a target NN filter is the same with the target filter, wherein the target filter is one of the first NN filter, the second NN filter, or the third NN filter.
Clause 79. The method of any of clauses 75-77, wherein a function of a target NN filter is a simplified version of the target filter, wherein the target filter is one of the first NN filter, the second NN filter, or the third NN filter.
Clause 80. The method of any of clauses 75-77, wherein a function of a target NN filter is dependent on the target filter, wherein the target filter is one of the first NN filter, the second NN filter, or the third NN filter.
Clause 81. The method of any of clauses 75-77, wherein a function of a target NN filter is adaptive for different implementations of the target filter, wherein the target filter is one of the first NN filter, the second NN filter, or the third NN filter.
Clause 82. The method of clause 59, wherein an order of fusion candidates of the plurality of filters is adaptive.
Clause 83. The method of clause 59, wherein an order of fusion candidates of the plurality of filters is dependent on coding statistics of the video unit.
Clause 84. The method of clause 59, wherein an order of fusion candidates of the plurality of filters is pre-designed.
Clause 85. The method of clause 59, wherein one or each of fusion candidates only comprises NN filters.
Clause 86. The method of clause 59, wherein one or each of fusion candidates comprises NN filters and Non-NN filters.
Clause 87. The method of clause 86, wherein a Non-NN filter is one of the following, or is a group comprising at least one of the following: a deblocking filter, a sample adaptive offset (SAO) filter, a bilateral in-loop filter (BIF), an adaptive loop filter (ALF), a cross-component SAO (CCSAO) filter, or a cross-component ALF (CCALF).
Clause 88. The method of clause 1, wherein whether to and/or a way to utilize a fusion result of the plurality of filters is dependent on at least one of: a coding mode of the video unit, a coding statistic of the video unit, a prediction mode, QP, a temporal layer, a slice type, a quantization step, a block size of the video unit, color components, or a signal in the bitstream.
Clause 89. The method of clause 88, wherein the signal is in at least one of: a sequence, a picture, a slice, a tile, a brick, a subpicture, a coding tree unit (CTU), a coding tree block (CTB), a CTU row, a CTB row, a coding unit (CU), a coding block (CB), a plurality of CUs, or a plurality of CBs.
Clause 90. The method of clause 1, wherein the number of filters in the plurality of filters is an integer number.
Clause 91. The method of clause 90, wherein the number of filters is 0, 1, 2, 3, 4, 5, or 6, or wherein the number of filters is depending on a statistic of the video unit.
Clause 92. The method of clause 91, wherein the statistic comprises at least one of: a prediction mode, QP, a temporal layer, or a slice type.
Clause 93. The method of clause 91, wherein usage of the plurality of filters is dependent on an indicator in at least one of: a sequence, a picture, a slice, a tile, a brick, a subpicture, a coding tree unit (CTU), a coding tree block (CTB), a CTU row, a CTB row, a coding unit (CU), a coding block (CB), a plurality of CUs, or a plurality of CBs.
Clause 94. The method of clause 1, wherein the plurality of filters are a group of filters.
Clause 95. The method of clause 88, wherein clipping is applied to samples due to the fusion result of the plurality of filters.
Clause 96. The method of clause 95, wherein the clipping is dependent on coding modes and/or coding statistics of the video unit.
Clause 97. The method of clause 83 or 96, wherein the coding statistics comprise at least one of a prediction mode, a quantization parameter (QP), a temporal layer, or a slice type.
Clause 98. The method of clause 95, wherein the clipping is dependent on a bit depth of an input signal and/or internal signal of the plurality of filters.
Clause 99. The method of clause 88, wherein the fusion result is put into a decoded picture buffer.
Clause 100. The method of clause 88, wherein the fusion result is a final display signal.
Clause 101. The method of clause 1, wherein a model of a first filter in the plurality of filters is a simplified version of a model of a second filter in the plurality of filters.
Clause 102. The method of clause 101, wherein the plurality of filters are NN filters.
Clause 103. The method of clause 102, wherein depth of models of the NN filters are different, wherein feature maps of the models of the NN filters are different, wherein the number of residual blocks of the models of the NN filters are different, or wherein a convolution kernel of the models of the NN filters are different.
Clause 104. The method of clause 103, wherein models of the NN filter used in the applying have a shallower depth.
Clause 105. The method of clause 103, wherein the models of the NN filters have less feature maps.
Clause 106. The method of clause 103, wherein the number of residual blocks of models of the NN filters used in the applying are less, or wherein the number of residual blocks is 1, 2, 3, 4, 5, or 6.
Clause 107. The method of clause 102, wherein a simplified model and a normal model of the plurality of filters are used in the applying.
Clause 108. A method of video processing, comprising: determining, during a conversion between a video unit of a video and a bitstream of the video unit, at least one syntax element indicating enabling of combined applying of a plurality of filters; and performing the conversion based on the at least one syntax element.
Clause 109. The method of clause 108, wherein the at least one syntax element is indicated at a first level.
Clause 110. The method of clause 109, wherein the first level is a sequence level, and the at least one syntax element is comprised in a sequence parameter set (SPS) or sequence header.
Clause 111. The method of clause 109, wherein the at least one syntax element comprises a first flag indicating whether the combined applying is enabled.
Clause 112. The method of clause 111, wherein the combined applying is enabled if the first flag is true or 1, or the combined applying is not enabled if the flag is false or 0.
Clause 113. The method of clause 109, wherein the at least one syntax element at the first level comprises a syntax element indicating the number of fusion modes which are potentially used in the combined applying of the plurality of filters.
Clause 114. The method of clause 113, wherein the at least one syntax element is signaled only if the combined applying is enabled.
Clause 115. The method of clause 109, wherein the at least one syntax element at the first level comprises a syntax element indicating whether the combined applying is to be used in the first level.
Clause 116. The method of clause 109, wherein the at least one syntax element at the first level comprises a syntax element indicating whether the combined applying can be adaptively/non-adaptive used or selected in a second level.
Clause 117. The method of clause 108, wherein the at least one syntax element is indicated at a second level different from a first level.
Clause 118. The method of clause 117, wherein the second level is a picture level or a slice level.
Clause 119. The method of clause 118, wherein the second level is the picture level and the at least one syntax element is comprised in a picture header (PH) or picture parameter set (PPS).
Clause 120. The method of clause 118, wherein the second level is the slice level and the at least one syntax element is comprised in a slice header (SH).
Clause 121. The method of clause 117, wherein the at least one syntax element at the second level is conditionally indicated in a bitstream.
Clause 122. The method of clause 121, wherein whether the at least one syntax element is indicated is based on one or more syntax elements indicated at the first level.
Clause 123. The method of clause 117, wherein the at least one syntax element indicated at the second level comprises a first flag indicating whether the combined applying is enabled in the second level.
Clause 124. The method of clause 117, wherein the at least one syntax element indicated at the second level comprises a syntax element indicating the number of fusion modes which can be used in the second level.
Clause 125. The method of clause 124, wherein the number of fusion modes is a default value.
Clause 126. The method of clause 125, wherein the default value is 0, 1, 2, or 3.
Clause 127. The method of clause 124, wherein the at least one syntax element is not indicated in a bitstream.
Clause 128. The method of clause 117, wherein the at least one syntax element indicated at the second level comprises a syntax element indicating whether the combined applying is to be used at the second level.
Clause 129. The method of clause 117, wherein the at least one syntax element indicated at the second level comprises a syntax element indicating an index of a fusion candidate of the plurality of filters.
Clause 130. The method of clause 129, wherein the index of the fusion candidate is the same as an indicator of the index of a selecting filter.
Clause 131. The method of clause 129, wherein whether the at least one syntax element is indicated is based on syntax elements indicating the number of fusion modes.
Clause 132. The method of clause 117, wherein the at least one syntax element indicated at the second level comprises a syntax element indicating fusion parameters.
Clause 133. The method of clause 132, wherein the at least one syntax element indicates the number of filters used in one fusion mode.
Clause 134. The method of clause 132, wherein the combined applying of the plurality of filters is based on a linear mode represented by:
Clause 135. The method of clause 134, wherein ak is equal to a value of the at least one syntax element multiply/divided by a factor T.
Clause 136. The method of clause 135, wherein the factor T is equal to 2{circumflex over ( )}W, 2{circumflex over ( )}W represents 2 to the power of W, wherein W is a positive integer, or W is one of 0, 2, 4, 6, 8, 10, 12, 14, or 16. Clause 137. The method of clause 135, wherein T is a positive integer.
Clause 138. The method of clause 134, wherein whether the at least one syntax element is to be indicated in the bitstream is dependent on a previous indirect syntax element.
Clause 139. The method of clause 132, wherein syntax elements for fusion candidates of the plurality of filters are different.
Clause 140. The method of clause 117, wherein the at least one syntax element at a second level comprises a syntax element indicating whether the combined applying can be adaptively/non-adaptive used or selected at a third level.
Clause 141. The method of clause 108, wherein the at least one syntax element is indicated at a third level, the third level being different from a first level or a second level.
Clause 142. The method of clause 141, wherein the third level corresponds to one of a patch, a coding tree unit (CTU), a coding tree block (CTB), a block, a subpicture, a tile, a slice, or a region containing multiple samples.
Clause 143. The method of clause 141, wherein the at least one syntax element at the third level is conditionally indicated in a bitstream.
Clause 144. The method of clause 141, wherein whether the at least one syntax element is indicated is based on one or more syntax elements indicated at the first level or the second level.
Clause 145. The method of clause 141, wherein the at least one syntax element indicated at the third level comprises a first flag indicating whether the combined applying is enabled in the third level.
Clause 146. The method of clause 141, wherein the at least one syntax element indicated at the third level comprises a syntax element indicating whether the combined applying is to be used in the third level.
Clause 147. The method of clause 141, wherein the at least one syntax element indicated at the third level comprises a syntax element indicating an index of a fusion candidate of the plurality of filters.
Clause 148. The method of clause 147, wherein the index of the fusion candidate is the same as an indicator of the index of a selecting filter.
Clause 149. The method of clause 147, wherein whether the at least one syntax element is indicated is based on syntax elements indicating the number of fusion modes in the second level.
Clause 150. The method of clause 147, wherein whether the at least one syntax element is indicated is based on syntax elements indicating the number of indices of fusion candidates in the second level.
Clause 151. The method of clause 141, wherein the at least one syntax element indicated at the third level comprises a syntax element indicating fusion parameters.
Clause 152. The method of clause 151, wherein the at least one syntax element indicating whether to use the fusion parameters in the second level or the third level.
Clause 153. The method of clause 151, wherein one of the at least one syntax element at the third level is conditionally signaled.
Clause 154. The method of clause 153, wherein whether the at least one syntax element at the third level is indicated is based on a syntax element indicating whether to use the fusion parameters in the second level or in the third level.
Clause 155. The method of clause 141, wherein the at least one syntax element indicates the number of filters used in one fusion mode.
Clause 156. The method of clause 141, wherein the combined applying of the plurality of filters is based on a linear mode represented by:
Clause 157. The method of clause 156, wherein ak is equal to a value of the at least one syntax element multiply/divided by a factor T.
Clause 158. The method of clause 157, wherein the factor T is equal to 2{circumflex over ( )}W, 2{circumflex over ( )}W represents 2 to the power of W, wherein W is a positive integer, or W is one of 0, 2, 4, 6, 8, 10, 12, 14, or 16. Clause 159. The method of clause 157, wherein T is a positive integer.
Clause 160. The method of clause 156, wherein whether the at least one syntax element is to be indicated in the bitstream is dependent on a previous indirect syntax element.
Clause 161. The method of clause 141, wherein syntax elements for fusion candidates of the plurality of filters are different.
Clause 162. The method of clause 108, wherein one of the at least one syntax element is set to a default value.
Clause 163. The method of clause 162, wherein the at least one syntax element is not indicated in a bitstream.
Clause 164. The method of clause 162, wherein a first syntax element of the at least one syntax element is set to a default value only if the first syntax element is not indicated in the bitstream.
Clause 165. The method of any of clauses 162 to 164, wherein the default value is one of −1, 0, 1, 2, 3, or 4.
Clause 166. The method of clause 108, wherein the at least one syntax element is indicated by context coding or bypass coding.
Clause 167. The method of clause 108, wherein the at least one syntax element is binarized using one of the following: fixed length coding, or unary coding, or truncated unary coding, or signed unary coding, or signed truncated unary coding, or truncated binary coding, or k-th exponential golomb coding.
Clause 168. The method of clause 167, wherein k is a positive integer, or wherein k is equal to 0, 1, 2, 3, 4, 5, or 6.
Clause 169. The method of clause 108, wherein the at least one syntax element is indicated individually for different color components.
Clause 170. The method of clause 169, wherein the at least one syntax element is indicated only for a first set of color components.
Clause 171. The method of clause 170, wherein the first set of color components comprise Y or Cb or Cr color components.
Clause 172. The method of clause 170, wherein the first set of color components comprise R or G or B color components.
Clause 173. The method of clause 170, wherein information of components other than the first set of color components is indicated by one or more syntax elements of a second set of color components.
Clause 174. The method of clause 169, wherein the at least one syntax element is indicated for all available color components.
Clause 175. The method of clause 169, wherein the at least one syntax element is indicated for Luma color components.
Clause 176. The method of clause 169, wherein the at least one syntax element is indicated for Chroma color components.
Clause 177. The method of clause 176, wherein Cb and Cr color components share the same syntax elements.
Clause 178. The method of clause 169, wherein the at least one syntax element is indicated for Y and/or Cb and/or Cr color components.
Clause 179. The method of clause 169, wherein the at least one syntax element is indicated for R and/or G and/or B color components.
Clause 180. The method of clause 175, wherein a Luma color component indicates a Y component.
Clause 181. The method of clause 176, wherein a Chroma color component indicates a Cb or Cr component.
Clause 182. The method of clause 169, wherein the at least one syntax element is indexed by the color components.
Clause 183. The method of clause 108, wherein the plurality of filters is applied in combination to a NN based coding method.
Clause 184. The method of clause 183, wherein at least one of the plurality of filters is replaced by an intra prediction method.
Clause 185. The method of clause 184, wherein the intra prediction method is a NN based method or a non-NN based method.
Clause 186. The method of clause 183, wherein at least one of the plurality of filters is replaced by an inter prediction method.
Clause 187. The method of clause 186, wherein the inter prediction method is a NN based method or a non-NN based method.
Clause 188. The method of clause 183, wherein the plurality of filters are applied to an unified NN filtering method, or wherein the plurality of filters is applied to a non-unified NN filtering method.
Clause 189. The method of clause 183, wherein the plurality of filters are applied to at least one of: a NN based intra method or a NN based inter method.
Clause 190. The method of clause 183, wherein the plurality of filters are applied to at least one of: a non-NN based intra method or a non-NN based inter method.
Clause 191. The method of clause 183, wherein one filter of the plurality of filters is a NN based intra or inter method, and another filter of the plurality of filters is a non-NN based intra or inter method.
Clause 192. The method of clause 191, wherein the one filter and the other filter of the plurality of filters are combined.
Clause 193. The method of any of clauses 1-192, wherein the conversion includes encoding the video unit into the bitstream.
Clause 194. The method of any of clauses 1-192, wherein the conversion includes decoding the video unit from the bitstream.
Clause 195. An apparatus for processing video data comprising a processor and a non-transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform a method in accordance with any of clauses 1-192.
Clause 196. A non-transitory computer-readable storage medium storing instructions that cause a processor to perform a method in accordance with any of clauses 1-192.
Clause 197. A non-transitory computer-readable recording medium storing a bitstream of a video unit of a video which is generated by a method performed by a video processing apparatus, wherein the method comprises: applying a plurality of filters in combination based on a model to the video unit; and generating the bitstream of the video unit based on the applying.
Clause 198. A method for storing bitstream of a video, comprising: applying a plurality of filters in combination based on a model to a video unit of a video; generating a bitstream of the video unit based on the applying; and storing the bitstream in a non-transitory computer-readable recording medium.
Clause 199. A non-transitory computer-readable recording medium storing a bitstream of a video unit of a video which is generated by a method performed by a video processing apparatus, wherein the method comprises: determining at least one syntax element indicating enabling of combined applying of a plurality of filters; and generating a bitstream of the video unit based on the at least one syntax element.
Clause 200. A method for storing a bitstream of a video, comprising: determining at least one syntax element indicating enabling of combined applying of a plurality of filters; generating a bitstream of a video unit of the video based on the at least one syntax element; and storing the bitstream in a non-transitory computer-readable recording medium.
It would be appreciated that the computing device 1800 shown in
As shown in
In some embodiments, the computing device 1800 may be implemented as any user terminal or server terminal having the computing capability. The server terminal may be a server, a large-scale computing device or the like that is provided by a service provider. The user terminal may for example be any type of mobile terminal, fixed terminal, or portable terminal, including a mobile phone, station, unit, device, multimedia computer, multimedia tablet, Internet node, communicator, desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, personal communication system (PCS) device, personal navigation device, personal digital assistant (PDA), audio/video player, digital camera/video camera, positioning device, television receiver, radio broadcast receiver, E-book device, gaming device, or any combination thereof, including the accessories and peripherals of these devices, or any combination thereof. It would be contemplated that the computing device 1800 can support any type of interface to a user (such as “wearable” circuitry and the like).
The processing unit 1810 may be a physical or virtual processor and can implement various processes based on programs stored in the memory 1820. In a multi-processor system, multiple processing units execute computer executable instructions in parallel so as to improve the parallel processing capability of the computing device 1800. The processing unit 1810 may also be referred to as a central processing unit (CPU), a microprocessor, a controller or a microcontroller.
The computing device 1800 typically includes various computer storage medium. Such medium can be any medium accessible by the computing device 1800, including, but not limited to, volatile and non-volatile medium, or detachable and non-detachable medium. The memory 1820 can be a volatile memory (for example, a register, cache, Random Access Memory (RAM)), a non-volatile memory (such as a Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), or a flash memory), or any combination thereof. The storage unit 1830 may be any detachable or non-detachable medium and may include a machine-readable medium such as a memory, flash memory drive, magnetic disk or another other media, which can be used for storing information and/or data and can be accessed in the computing device 1800.
The computing device 1800 may further include additional detachable/non-detachable, volatile/non-volatile memory medium. Although not shown in
The communication unit 1840 communicates with a further computing device via the communication medium. In addition, the functions of the components in the computing device 1800 can be implemented by a single computing cluster or multiple computing machines that can communicate via communication connections. Therefore, the computing device 1800 can operate in a networked environment using a logical connection with one or more other servers, networked personal computers (PCs) or further general network nodes.
The input device 1850 may be one or more of a variety of input devices, such as a mouse, keyboard, tracking ball, voice-input device, and the like. The output device 1860 may be one or more of a variety of output devices, such as a display, loudspeaker, printer, and the like. By means of the communication unit 1840, the computing device 1800 can further communicate with one or more external devices (not shown) such as the storage devices and display device, with one or more devices enabling the user to interact with the computing device 1800, or any devices (such as a network card, a modem and the like) enabling the computing device 1800 to communicate with one or more other computing devices, if required. Such communication can be performed via input/output (I/O) interfaces (not shown).
In some embodiments, instead of being integrated in a single device, some or all components of the computing device 1800 may also be arranged in cloud computing architecture. In the cloud computing architecture, the components may be provided remotely and work together to implement the functionalities described in the present disclosure. In some embodiments, cloud computing provides computing, software, data access and storage service, which will not require end users to be aware of the physical locations or configurations of the systems or hardware providing these services. In various embodiments, the cloud computing provides the services via a wide area network (such as Internet) using suitable protocols. For example, a cloud computing provider provides applications over the wide area network, which can be accessed through a web browser or any other computing components. The software or components of the cloud computing architecture and corresponding data may be stored on a server at a remote position. The computing resources in the cloud computing environment may be merged or distributed at locations in a remote data center. Cloud computing infrastructures may provide the services through a shared data center, though they behave as a single access point for the users. Therefore, the cloud computing architectures may be used to provide the components and functionalities described herein from a service provider at a remote location. Alternatively, they may be provided from a conventional server or installed directly or otherwise on a client device.
The computing device 1800 may be used to implement video encoding/decoding in embodiments of the present disclosure. The memory 1820 may include one or more video coding modules 1825 having one or more program instructions. These modules are accessible and executable by the processing unit 1810 to perform the functionalities of the various embodiments described herein.
In the example embodiments of performing video encoding, the input device 1850 may receive video data as an input 1870 to be encoded. The video data may be processed, for example, by the video coding module 1825, to generate an encoded bitstream. The encoded bitstream may be provided via the output device 1860 as an output 1880.
In the example embodiments of performing video decoding, the input device 1850 may receive an encoded bitstream as the input 1870. The encoded bitstream may be processed, for example, by the video coding module 1825, to generate decoded video data. The decoded video data may be provided via the output device 1860 as the output 1880.
While this disclosure has been particularly shown and described with references to preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present application as defined by the appended claims. Such variations are intended to be covered by the scope of this present application. As such, the foregoing description of embodiments of the present application is not intended to be limiting.
Number | Date | Country | Kind |
---|---|---|---|
PCT/CN2022/075116 | Jan 2022 | WO | international |
This application is a continuation of International Application No. PCT/CN2023/073743, filed on Jan. 29, 2023, which claims the benefit of International Application No. PCT/CN2022/075116, filed on Jan. 29, 2022. The entire contents of these applications are hereby incorporated by reference in their entireties.
Number | Date | Country | |
---|---|---|---|
Parent | PCT/CN2023/073743 | Jan 2023 | WO |
Child | 18787879 | US |