Geometric transformations in neural network-based coding tools for video coding

Abstract

A mechanism for processing video data is disclosed. The mechanism determines to modify the video unit during application of the video compression function. The modification may include applying a geometric transformation to the video unit. A conversion is performed between the visual media data and the bitstream based on the modified video unit.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to and the benefit of U.S. Provisional Patent Application No. 63 / 358,745, filed on July 6, 2022. The above patent application is incorporated herein by reference in its entirety. Technical Field

[0003] The present disclosure relates to the generation, storage and consumption of digital audio-visual media information in file format. Background Art

[0004] Digital video accounts for the largest use of bandwidth on the Internet and other digital communications networks. As the number of connected user devices capable of receiving and displaying video increases, bandwidth demands for digital video usage are likely to continue to grow. Summary of the invention

[0005] A first aspect relates to a method for processing video data, comprising: determining to modify a video unit in the process of applying a video compression function; and performing conversion between visual media data and a bitstream based on the modified video unit.

[0006] A second aspect relates to an apparatus for processing video data, comprising: a processor; and a non-transitory memory having instructions thereon, wherein the instructions, when executed by the processor, cause the processor to perform any of the preceding aspects.

[0007] A third aspect relates to a non-transitory computer-readable medium, including a computer program product for use by a video codec device, the computer program product including computer executable instructions stored on the non-transitory computer-readable medium, so that when executed by a processor, the video codec device performs any one of the methods of the aforementioned aspects.

[0008] A fourth aspect relates to a non-transitory computer-readable recording medium storing a bitstream of a video generated by a method performed by a video processing device, wherein the method includes: determining that a video unit is modified during application of a video compression function; and generating a bitstream based on the determination.

[0009] A fifth aspect relates to a method for storing a bitstream of a video, comprising: determining that a video unit is modified during application of a video compression function; generating a bitstream based on the determination; and storing the bitstream in a non-transitory computer-readable recording medium.

[0010] For clarity, any of the foregoing embodiments may be combined with any or more of the other foregoing embodiments to create new embodiments within the scope of the present disclosure.

[0011] These and other features will become more clearly understood from the following detailed description taken in conjunction with the accompanying drawings and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] For a more complete understanding of the present disclosure, reference is now made to the following brief description, taken in conjunction with the accompanying drawings and detailed description, wherein like reference numerals represent like parts.

[0013] Figure 1 An exemplary picture is shown segmented into raster scan strips.

[0014] Figure 2 An exemplary picture segmented into rectangular scan strips is shown.

[0015] Figure 3 An exemplary picture segmented into slices is shown.

[0016] Figure 4 An example of a codec tree block (CTB) that crosses a picture boundary is shown.

[0017] Figure 5 Examples of picture samples on an 8x8 grid and horizontal and vertical block boundaries are shown.

[0018] Figure 6 An example of pixels involved in filter on / off decisions and strong / weak filter selection is shown.

[0019] Figure 7 Four one-dimensional (1-D) directional patterns for edge offset (EO) sample classification are shown.

[0020] Figure 8 An example of a filter shape for an adaptive loop filter (ALF) is shown.

[0021] Fig. 9 An example of transform coefficients for a 5x5 diamond filter support is shown.

[0022] Fig.10 An example of relative coordinates for a 5x5 diamond filter support is shown.

[0023] Fig.11 An exemplary convolutional neural network (CNN) architecture is shown.

[0024] Fig.12 An exemplary vertical flip is shown.

[0025] Fig.13 An exemplary horizontal flip is shown.

[0026] Fig.14 An exemplary 180 degree rotation is shown.

[0027] Fig.15 An exemplary 90 degree rotation is shown.

[0028] Fig.16 An exemplary 270 degree rotation is shown.

[0029] Fig.17 An exemplary extended input block including samples from the current video unit and neighboring video units is shown.

[0030] Fig.18 is a block diagram illustrating an exemplary video processing system.

[0031] Fig.19 is a block diagram of an exemplary video processing device.

[0032] Fig. 20 is a flow chart of an exemplary video processing method.

[0033] Fig.21 is a block diagram illustrating an exemplary video coding system.

[0034] Fig. 22 is a block diagram illustrating an exemplary encoder.

[0035] Fig.23 is a block diagram illustrating an exemplary decoder.

[0036] Fig.24 is a schematic diagram of an exemplary encoder. DETAILED DESCRIPTION

[0037] It should be understood at the outset that although illustrative implementations of one or more embodiments are provided below, the disclosed systems and / or methods may be implemented using any number of techniques, whether currently known or yet to be developed. The present disclosure should not be limited in any way to the illustrative implementations, drawings, and techniques shown below, including the exemplary designs and implementations shown and described herein, but may be modified within the full scope of the appended claims and their equivalents.

[0038] The section headings used in this document are for ease of understanding and do not limit the applicability of the techniques and embodiments disclosed in each section to only that section. In addition, the techniques described herein are applicable to other video codec protocols and designs.

[0039] 1. Preliminary Discussion

[0040] This document relates to video coding techniques. Specifically, it relates to loop filtering in image and / or video coding. These ideas can be applied alone or in various combinations to video codecs, such as High Efficiency Video Codec (HEVC), Versatile Video Codec (VVC), Audio Video Codec (AVC) Version 3 (AVC), or other video coding techniques. It can also be applied to other video coding standards or video codecs, or used as a post-processing method outside the encoding and / or decoding process.

[0041] 2. Video Codec Standards

[0042] Video codec standards have evolved primarily through the development of International Telecommunication Union-Telecommunication Standardization Sector (ITU-T) and International Organization for Standardization (ISO) / International Electrotechnical Commission (IEC) standards. ITU-T developed H.261 and H.263, ISO / IEC developed Moving Picture Experts Group (MPEG)-1 and MPEG-4 Visual, and the two organizations jointly developed H.262 / MPEG-2 Video and H.264 / MPEG-4 Advanced Video Codec (AVC) and H.265 / HEVC standards. Since H.262, video codec standards have been based on a hybrid video codec structure that utilizes temporal prediction plus transform codecs. To explore future video codec technologies beyond HEVC, the Video Codec Experts Group (VCEG) and MPEG jointly established the Joint Video Exploration Team (JVET). JVET has adopted many methods and input them into a reference software called the Joint Exploration Model (JEM). JVET was created between VCEG and ISO / IEC JTC1 SC29 / WG11 (MPEG) to work on the VVC standard with the goal of reducing bitrate by 50% compared to HEVC.

[0043] 2.1 Color Space and Chroma Subsampling

[0044] A color space, also called a color model (or color system), is a mathematical model that describes the range of colors as a tuple of numbers, such as 3 or 4 values ​​or color components (e.g., RGB). In general, a color space is a detailed description of coordinate systems and subspaces. For video compression, the most commonly used color spaces are luminance, blue-difference chrominance, and red-difference chrominance (YCbCr) and red, green, blue (RGB).

[0045] YCbCr, Y'CbCr, or Y Pb / Cb Pr / Cr, also written as YCBCR or Y'CBCR, is a family of color spaces used as part of the color imaging pipeline in video and digital photography systems. Y' is the luminance component, and CB and CR are the blue difference chrominance and red difference chrominance components. Y' (with superscript notation) is different from Y, which is luminance, meaning that light intensity is non-linearly encoded based on the gamma-corrected RGB primaries.

[0046] Chroma subsampling is the practice of encoding an image at a lower resolution for chroma information than for luminance information by taking advantage of the fact that the human visual system is less sensitive to color differences than to luminance. 2.1.1 4:4:4

[0048] In 4:4:4, each of the three Y'CbCr components has the same sampling rate. Therefore, there is no chroma subsampling. This scheme is sometimes used in high-end film scanners and film post-production. 2.1.2 4:2:2

[0050] In 4:3:2, the two chroma components are sampled at half the luma sampling rate. The horizontal chroma resolution is halved. This reduces the bandwidth of the uncompressed video signal by one third, but there is little visual difference. 2.1.3 4:2:0

[0052] Compared to 4:1:1, the horizontal sampling in 4:2:0 is doubled, but the vertical resolution is halved because in this scheme, the Cb and Cr channels are sampled only on every alternate line. Therefore, the data rate is the same. Cb and Cr are each subsampled by a factor of 2 in the horizontal and vertical directions. There are three variants of the 4:2:0 scheme with different horizontal and vertical addressing.

[0053] In MPEG-2, Cb and Cr are co-located horizontally. Cb and Cr are located between pixels in the vertical direction (in the gaps). In JPEG / JPEG File Interchange Format (JFIF), H.261, and MPEG-1, Cb and Cr are located in the middle gaps between alternate luminance samples. In 4:2:0DV, Cb and Cr are co-located horizontally. Vertically, they are co-located on alternate lines.

[0054] 2.2 Definition of Video Unit

[0055] A picture is divided into one or more slice rows and one or more slice columns. A slice is a sequence of codec tree units (CTUs) covering a rectangular area of ​​a picture. A slice can be divided into one or more bricks, each brick comprising multiple CTU rows within the slice. Slices that are not divided into multiple bricks may also be referred to as bricks. However, bricks that are true subsets of a slice may not be referred to as slices. A slice may include either multiple slices of a picture, or multiple bricks of a slice.

[0056] Two strip modes are supported, raster scan strip mode and rectangular strip mode. In raster scan strip mode, a strip contains a sequence of slices in a raster scan of a slice of an image. In rectangular strip mode, a strip contains multiple bricks of an image, which together form a rectangular region of the image. The bricks within a rectangular strip are arranged in the order of the brick raster scan of the strip. Figure 1 An example of raster scan stripe partitioning of a picture with 18×12 luma CTUs is shown, where the picture is divided into 12 slices and 3 raster scan stripes.

[0057] Figure 2 An example of rectangular slice partitioning of a picture with 18×12 luma CTUs is shown, where the picture is divided into 24 slices (6 slice columns and 4 slice rows) and 9 rectangular slices.

[0058] Figure 3 An example showing an image partitioned into slices, bricks, and rectangular strips, where the image is divided into 4 slices (2 slice columns and 2 slice rows), 11 bricks (the upper left slice contains 1 brick, the upper right slice contains 5 bricks, the lower left slice contains 2 bricks, and the lower right slice contains 3 bricks), and 4 rectangular strips.

[0059] 2.2.1 CTU / CTB size

[0060] In VVC, the CTU size signaled by the syntax element log2_ctu_size_minus2 in the sequence parameter set (SPS) can be as small as 4×4.

[0061] 7.3.2.3 Sequence parameter set RBSP syntax

[0062]

[0063]

[0064]

[0065]

[0066] log2_ctu_size_minus2 plus 2 specifies the luma coding tree block size for each CTU. log2_min_luma_coding_block_size_minus2 plus 2 specifies the minimum luma coding block size. The variables CtbLog2SizeY, CtbSizeY, MinCbLog2SizeY, MinCbSizeY, MinTbLog2SizeY, MaxTbLog2SizeY, MinTbSizeY, MaxTbSizeY, PicWidthInCtbsY, PicHeightInCtbsY, PicSizeInCtbsY, PicWidthInMinCbsY, PicHeightInMinCbsY, PicSizeInMinCbsY, PicSizeInSamplesY, PicWidthInSamplesC, and PicHeightInSamplesC are derived as follows:

[0067] CtbLog2SizeY=log2_ctu_size_minus2+2 (7-9)

[0068] CtbSizeY=1< <CtbLog2SizeY (7-10)

[0069] MinCbLog2SizeY=log2_min_luma_coding_block_size_minus2+2 (7-11)

[0070] MinCbSizeY=1< <MinCbLog2SizeY (7-12)

[0071] MinTbLog2SizeY=2 (7-13)

[0072] MaxTbLog2SizeY=6 (7-14)

[0073] MinTbSizeY=1< <MinTbLog2SizeY (7-15)

[0074] MaxTbSizeY=1< <MaxTbLog2SizeY (7-16)

[0075] PicWidthInCtbsY=Ceil(pic_width_in_luma_samples÷CtbSizeY) (7-17)

[0076] PicHeightInCtbsY = Ceil(pic_height_in_luma_samples ÷ CtbSizeY) (7-18)

[0077] PicSizeInCtbsY = PicWidthInCtbsY * PicHeightInCtbsY (7-19)

[0078] PicWidthInMinCbsY = pic_width_in_luma_samples / MinCbSizeY (7-20)

[0079] PicHeightInMinCbsY = pic_height_in_luma_samples / MinCbSizeY (7-21)

[0080] PicSizeInMinCbsY = PicWidthInMinCbsY * PicHeightInMinCbsY (7-22)

[0081] PicSizeInSamplesY = pic_width_in_luma_samples * pic_height_in_luma_samples(7-23)

[0082] PicWidthInSamplesC = pic_width_in_luma_samples / SubWidthC (7-24)

[0083] PicHeightInSamplesC = pic_height_in_luma_samples / SubHeightC (7-25)

[0084] 2.2.2 CTUs in the Picture

[0085] Assume that the CTB / largest coding unit (LCU) size is represented by M × N (usually M equals N), and for a CTB located at the picture boundary (or a slice or strip or other type of boundary, taking the picture boundary as an example), K × L samples are within the picture boundary, where K < M or L < N. For those CTBs depicted as Figure 4 shown (showing examples of CTBs straddling the picture boundary), the CTB size is still equal to M × N. However, the bottom boundary / right boundary of the CTB is outside the picture.

[0086] 2.3 Encoding and Decoding Processes of the Video Codec

[0087] Fig.24 An example of an encoder block diagram of VVC is shown, which includes three loop filter blocks: deblocking filter (DF) 4602, sample adaptive offset (SAO) 4604 and ALF 4606. Unlike DF 4602, which uses a predefined filter, SAO 4604 and ALF 4606 use the original samples of the current picture to reduce the mean square error between the original samples and the reconstructed samples by adding an offset and applying a finite impulse response (FIR) filter, respectively, where the codec's side information signals the offset and filter coefficients. ALF 4606 is located at the last processing stage of each picture and can be seen as a tool to capture and repair artifacts generated by the previous stage.

[0088] 2.4 Deblocking Filter

[0089] The input to the deblocking (DB) filter is the reconstructed samples before the loop filter. The vertical edges in the picture are filtered first. Then, the horizontal edges in the picture are filtered using the samples modified by the vertical edge filtering process as input. The vertical and horizontal edges in the CTB of each CTU are processed separately on a codec unit basis. The vertical edges of the codec blocks in the codec unit are filtered starting from the edge on the left hand side of the codec block, and proceeding through the edges to the right hand side of the codec block in their geometric order. The horizontal edges of the codec blocks in the codec unit are filtered starting from the edge at the top of the codec block, and proceeding through the edges to the bottom of the codec block in their geometric order.

[0090] 2.4.1 Boundary Decision

[0091] Apply filtering to 8×8 block boundaries, such as Figure 5 (which shows picture samples on an 8×8 grid as well as horizontal and vertical block boundaries, and non-overlapping blocks of 8×8 samples, which can be deblocked in parallel). Furthermore, such boundaries must be transform block boundaries or codec sub-block boundaries, e.g. due to the use of affine motion prediction (ATMVP). For other boundaries, deblocking filtering is disabled.

[0092] 2.4.2 Boundary strength calculation

[0093] For transform block boundaries / codec sub-block boundaries, if the boundary is located in an 8×8 grid, the boundary can be filtered and the settings of bS[xDi][yDj] (where [xDi][yDj] represents coordinates) of the edge are defined as in Table 1 and Table 2, respectively.

[0094]

[0095]

[0096] Table 1 Boundary Strength (When SPS Intra Block Copy (IBC) is Disabled)

[0097]

[0098] Table 2 Boundary Strength (When SPS IBC is Enabled)

[0099] 2.4.3 Deblocking Decision for Luminance Component

[0100] In this subsection, the deblocking decision process is described. Figure 6 The pixels involved in the filter on / off decision and the strong / weak filter selection are shown. The wider and stronger luma filter is used only when conditions 1, 2, and 3 are all true. Condition 1 is the "large block condition". This condition detects whether the samples on the P side and Q side belong to large blocks, represented by the variables bSidePisLargeBlk and bSideQisLargeBlk, respectively. The definitions of bSidePisLargeBlk and bSideQisLargeBlk are as follows.

[0101] bSidePisLargeBlk = ((edge ​​type is vertical and p0 belongs to a CU with width>=32) || (edge ​​type is horizontal and p0 belongs to a CU with height>=32))? True: False

[0102] bSideQisLargeBlk = ((edge ​​type is vertical and q0 belongs to a CU with width>=32) || (edge ​​type is horizontal and q0 belongs to a CU with height>=32))? True: False

[0103] Based on bSidePisLargeBlk and bSideQisLargeBlk, condition 1 is defined as follows:

[0104] Condition 1 = (bSidePisLargeBlk || bSidePisLargeBlk)? True: False

[0105] Next, if condition 1 is true, condition 2 will be checked. First, the following variables are derived:

[0106] First, derive dp0, dp3, dq0, dq3 as in HEVC

[0107] if (side p is greater than or equal to 32)

[0108] dp0=(dp0+Abs(p50-2*p40+p30)+1)>>1

[0109] dp3=(dp3+Abs(p53-2*p43+p33)+1)>>1

[0110] if (q side is greater than or equal to 32)

[0111] dq0=(dq0+Abs(q50-2*q40+q30)+1)>>1

[0112] dq3=(dq3+Abs(q53-2*q43+q33)+1)>>1

[0113] Condition 2 = (d < β)? True: False

[0114] Where d=dp0+dq0+dp3+dq3.

[0115] If condition 1 and condition 2 are valid, then further check if any block uses sub-blocks:

[0116]

[0117] Sq=3

[0118] Finally, if both conditions 1 and 2 are valid, the deblocking method will check condition 3 (large block strong filter condition), which is defined as follows. In condition 3 StrongFilterCondition, the following variables are derived:

[0119] dpq is derived as in HEVC.

[0120] sp3 = Abs(p3 - p0), derived as in HEVC

[0121] if (side p is greater than or equal to 32)

[0122]

[0123] sq3 = Abs(q0 - q3), derived as in HEVC

[0124] if (q side is greater than or equal to 32)

[0125]

[0126] 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.

[0127] 2.2.4 Stronger Luminance Deblocking Filter (Designed for Larger Blocks)

[0128] When the samples on either side of the boundary belong to a large block, a bilinear filter is used. When the width of the vertical edge is >= 32 and the height of the horizontal edge is >= 32, the samples are defined as belonging to a large block. The bilinear filter is listed below. The block boundary samples pi from i=0 to Sp-1 and the block boundary samples qi from j=0 to Sq-1 in the above HEVC deblocking (pi and qi are the i-th samples in the row for filtering the vertical edge, or the i-th samples in the column for filtering the horizontal edge) are then replaced by linear interpolation as follows:

[0129] p i ′=(f i *Middle s,t +(64-f i )*P s +32)>>6), limit to p i ±tcPD i

[0130] q j ′=(g j *Middle s,t +(64-g j )*Q s +32)>>6), limit to q j ±tcPD j

[0131] where tcPD i and tcPD j The term is the position-dependent limit mentioned above, and g j 、f i 、Middle s,t , P s and Q s Given as follows:

[0132] 2.4.5 Chroma Deblocking Control

[0133] A chroma strong filter is 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 decision meets the following three conditions: The first condition is a decision for boundary strength and large blocks. The filter can be applied when the block width or height orthogonal to the block edge in the chroma sample domain is equal to or greater than 8. The second and third conditions are basically the same as the HEVC luma deblocking decision, which is an on / off decision and a strong filter decision, respectively.

[0134] In the first decision, the boundary strength (bS) is modified for chroma filtering, and the conditions are checked in order. If one condition is met, the remaining lower priority conditions 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 conditions are basically the same as the HEVC luma strong filter decision, as shown below.

[0135] In the second condition, d is derived as in HEVC luma deblocking. When d is less than β, the second condition will be true. In the third condition, StrongFilterCondition is derived as follows:

[0136] dpq is derived as in HEVC.

[0137] sp3 = Abs(p3 - p0), derived as in HEVC

[0138] sq3 = Abs(q0 - q3), derived as in HEVC

[0139] As in the 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)

[0140] 2.4.6 Strong Deblocking Filter for Chroma

[0141] The following strong deblocking filter for chroma is defined:

[0142] p2′=(3*p3+2*p2+p1+p0+q0+4)>>3

[0143] p1′=(2*p3+p2+2*p1+p0+q0+q1+4)>>3

[0144] p0′=(p3+p2+p1+2*p0+q0+q1+q2+4)>>3

[0145] The exemplary chroma filter performs deblocking on a 4x4 chroma sample grid.

[0146] 2.4.7 Position-dependent limiting

[0147] Position dependent clipping tcPD is applied to the output samples of the luminance filtering process, which involves modifying the strong and long filters of 7, 5 and 3 samples at the boundaries. Assuming a quantization error distribution, the clipping value can be increased for samples expected to have higher quantization noise, so the reconstructed sample values ​​are expected to deviate more from the true sample values.

[0148] For each P or Q boundary filtered with an asymmetric filter, a position-dependent threshold table is selected from two tables (e.g., Tc7 and Tc3 listed below) provided to the decoder as auxiliary information, depending on the result of the decision process:

[0149] Tc7={6,5,4,3,2,1,1}; Tc3={6,4,2};

[0150] tcPD=(Sp==3)? Tc3:Tc7;

[0151] tcQD=(Sq==3)? Tc3:Tc7;

[0152] For P or Q boundaries filtered with a short symmetric filter, a lower magnitude position-dependent threshold is applied:

[0153] Tc3 = {3, 2, 1};

[0154] After defining the threshold, the filtered p'i and q'i sample values ​​are limited according to the tcP and tcQ limit values:

[0155] p”i=Clip3(p’i+tcPi,p’i–tcPi,p’i);

[0156] q”j=Clip3(q’j+tcQj,q’j–tcQj,q’j);

[0157] Where p'i and q'i are the sample values ​​after filtering, p"i and q"j are the output sample values ​​after clipping, and tcPi is the clipping threshold derived from the VVC tc parameters and tcPD and tcQD. Function Clip3 is the clipping function specified in VVC.

[0158] 2.4.8 Sub-block deblocking adjustment

[0159] To implement parallel friendly deblocking using long filters and subblock deblocking, the long filter is restricted to modifying at most 5 samples on one side using subblock deblocking (AFFINE or ATMVP or decoder-side motion vector refinement (DMVR)), as shown in the luma control of the long filter. In addition, subblock deblocking is adjusted so that subblock boundaries close to codec unit (CU) or implicit TU boundaries on the 8×8 grid are restricted to modifying at most two samples on each side.

[0160] The following applies to sub-block boundaries that are not aligned with CU boundaries.

[0161]

[0162] Where edges equal to 0 correspond to CU boundaries, edges equal to 2 or equal to the orthogonal length -2 correspond to sub-block boundaries 8 samples from the CU boundary, etc. Where implicit-TU is true if implicit partitioning of TUs is used.

[0163] 2.5 Sample Adaptive Offset

[0164] The input of SAO is the reconstructed samples after DB. The concept of SAO is to reduce the average sample distortion of the region by first classifying the region samples into multiple categories using 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 offset of the region are encoded in the bitstream. In HEVC and VVC, the region (the unit of SAO parameter signaling) is defined as a codec tree unit (CTU). HEVC adopts two SAO types that can meet the low complexity requirements. These two types are edge offset (EO) and band offset (BO), which will be discussed in detail below. The index of the SAO type is encoded (in the range of [0, 2]). For EO, ​​sample classification is based on the comparison between the current sample and the adjacent samples according to the 1-D directional pattern: horizontal, vertical, 135° diagonal, and 45° diagonal.

[0165] Figure 7 Four one-dimensional (1-D) directional patterns for EO point classification are shown. These directional patterns include horizontal (EO class = 0), vertical (EO class = 1), 135° diagonal (EO class = 2), and 45° diagonal (EO class = 3).

[0166] For a given EO class, each sample inside the codec tree block (CTB) is classified into one of five categories. The current sample value, labeled "c", is compared with its two neighboring sample values ​​along the selected 1-D pattern. The classification rules for each sample are summarized in Table 3. Categories 1 and 4 are associated with local valleys and local peaks along the selected 1-D pattern, respectively. Categories 2 and 3 are associated with concave corners and convex corners along the selected 1-D pattern, respectively. If the current sample does not belong to EO category 1-4, it belongs to category 0 and SAO is not applied.

[0167] Table 3 Sample point classification rules for edge offset

[0168] category condition 1 c<a and c<b 2 (c<a&&c==b)||(c==a&&c<b) 3 (c>a&&c==b)||(c==a&&c>b) 4 c>a&&c>b 5 None of the above

[0169] 2.6 Adaptive Loop Filter Based on Geometric Transformation in JEM

[0170] The input of DB is the reconstructed samples after DB and SAO. The sample classification and filtering process is based on the reconstructed samples after DB and SAO. In JEM, a geometric transformation-based adaptive loop filter (GALF) with block-based filter adaptation is applied. For the luminance component, one of 25 filters is selected for each 2×2 block based on the direction and activity of the local gradient.

[0171] 2.6.1 Filter shape

[0172] In JEM, up to three diamond filter shapes can be selected for the luminance component (in Figure 8 ). An index is signaled at the picture level to indicate the filter shape used for the luma component. Each square represents a sample, and Ci (i is 0-6 (left), 0-12 (middle), 0-20 (right)) represents the coefficient applied to that sample. For the chroma components in a picture, a 5×5 diamond shape is always used.

[0173] 2.6.1.1 Block Classification

[0174] Each 2×2 block is classified into one of 25 classes. The class index C is based on its directionality D and activity The quantized value of is derived as follows:

[0175]

[0176] In order to calculate D and First, use the 1-D Laplacian to calculate the gradient in the horizontal, vertical, and two diagonal directions:

[0177]

[0178]

[0179] (5) The indices i and j refer to the coordinates of the top left sample point in the 2×2 block, and R(i,j) indicates the reconstructed sample point at the coordinate (i,j). Then the maximum and minimum values ​​of the gradient D in the horizontal and vertical directions are set to:

[0180]

[0181] And the maximum and minimum values ​​of the gradients in the two diagonal directions are set to:

[0182]

[0183] To derive the value of the directionality D, these values ​​are compared with each other and with two thresholds t1 and t2:

[0184] Step 1, if and If both are true, set D to 0.

[0185] Step 2, if Then continue from step 3; otherwise continue from step 4.

[0186] Step 3, if Then set D to 2; otherwise, set D to 1.

[0187] Step 4, if Then set D to 4; otherwise, set D to 3.

[0188] The activity value A is calculated as follows:

[0189]

[0190] A is further quantized to the range of 0 to 4 (including 0 and 4), and the quantized value is expressed as For the two chroma components in a picture, no classification method is applied, ie, a single set of ALF coefficients is applied for each chroma component.

[0191] 2.6.1.2 Filter Coefficient Geometric Transformation

[0192] Before filtering each 2×2 block, geometric transformations such as rotation or diagonal transformation and vertical flipping are applied to the filter coefficients f(k,l) associated with the coordinates (k,l) according to the gradient values ​​calculated for the block. This is equivalent to applying these transformations to the samples in the filter support region. The idea is to make different blocks with ALF applied more similar by aligning the directionality of different blocks.

[0193] Three geometric transformations are introduced, including diagonal transformation, vertical flip and rotation:

[0194] Diagonal transformation: f D (k,l)=f(l,k),

[0195] Flip vertically: f V (k,l)=f(k,Kl-1)

[0196] Rotation: f R (k,l)=f(Kl-1,k).

[0197] Where K is the size of the filter, and 0≤k,;≤K-1 are the coefficient coordinates such that position (0,0) is at the upper left corner and position (K-1,K-1) is at the lower right corner. The transform is applied to the filter coefficients f(k,l) according to the gradient value calculated for the block. Table 4 summarizes the relationship between the transform and the four gradients in the four directions. Fig. 9The transform coefficients for each position based on a 5×5 diamond are shown.

[0198] Gradient Value Transform <![CDATA[g d2 <g d1 And g h <g v ]]> No transformation <![CDATA[g d2 <g d1 And g v <g h ]]> Diagonal Transformation <![CDATA[g d1 <g d2 And g h <g v ]]> Flip Vertically <![CDATA[g d1 <g d2 And g v <g h ]]> Rotation

[0199] Table 4 shows the mapping of gradients and transformations computed by a block.

[0200] 2.6.1.3 Filter parameter signaling

[0201] In JEM, GALF filter parameters are signaled for the first CTU, i.e., after the slice header of the first CTU and before the SAO parameters. Up to 25 sets of luminance filter coefficients can be signaled. In order to reduce bit overhead, filter coefficients of different classifications can be merged. In addition, the GALF coefficients of the reference pictures are stored and allowed to be reused as GALF coefficients for the current picture. The current picture can choose to use the GALF coefficients stored for the reference picture and bypass the GALF coefficient signaling. In this case, only the index of one of the reference pictures is signaled, and the stored GALF coefficients of the indicated reference picture are inherited by the current picture.

[0202] In order to support GALF time 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 a picture, the corresponding filter set can be added to the candidate list. Once the size of the candidate list reaches the maximum allowed value (for example, 6 in JEM), the new filter set covers the oldest set in decoding order, that is, the first-in-first-out (FIFO) rule is applied to update the candidate list. In order to avoid duplication, the set can be added to the list only when the corresponding picture does not use GALF time prediction. In order 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 the temporal layer index (TempIdx) can constitute a filter set of a previously decoded picture equal to a lower TempIdx. For example, the kth array is assigned to be associated with a TempIdx equal to k, and it only includes filter sets from pictures with TempIdx less than or equal to k. After encoding or decoding a picture, the filter set associated with the picture will be used to update those arrays associated with equal or higher TempIdx.

[0203] Temporal prediction of the GALF coefficients is used for inter-coded frames to minimize signaling overhead. For intra-frames, temporal prediction is not available and a set of 16 fixed filters is assigned to each category. To indicate the use of fixed filters, the signaling notifies the flag of each category and, if necessary, the index of the selected fixed filter. Even when a fixed filter is selected for a given category, the coefficients of the adaptive filter f(k, l) can still be sent for that category, in which case the coefficients of the filter to be applied to the reconstructed image are the sum of the two coefficient sets.

[0204] The filtering process of the luma component can be controlled at the CU level. A flag is signaled to indicate whether GALF is applied to the luma component of the CU. For chroma components, whether GALF is applied is only indicated at the picture level.

[0205] 2.6.1.4 Filtering process

[0206] At the decoder side, when GALF is enabled for a block, each sample R(i,j) in the block is filtered to generate the sample value R′(i,j) as shown below, where L represents the filter length and f m,n denotes the filter coefficient, and f(k,l) denotes the decoded filter coefficient.

[0207]

[0208] Fig.10 An example of relative coordinates for a 5×5 diamond filter support is shown assuming that the coordinates (i, j) of the current sample point are (0, 0). Samples in different coordinates filled with the same color are multiplied by the same filter coefficients.

[0209] 2.7 Geometric Transformation-Based Adaptive Loop Filter (GALF) in VVC

[0210] 2.7.1GALF in VVC Test Model (VTM)-4

[0211] In VTM4.0, the filtering process of the adaptive loop filter is performed as follows:

[0212] O(x,y)=∑ (i,j) w(i,j).I(x+i,y+j), (11)

[0213] Among them, the sample point I (x + i, y + j) is the input sample point, O (x, y) is the output sample point after filtering (ie, the filter result), and w (i, j) represents the filter coefficient. In fact, in VTM4.0, it uses integer operations to implement fixed-point precision calculations:

[0214]

[0215] Where L represents the filter length, and where w(i,j) is the filter coefficient of fixed-point precision. Compared with JEM, VVC's GALF has the following major changes. The adaptive filter shape is removed. Only 7×7 filter shapes are allowed for the luminance component, and only 5×5 filter shapes are allowed for the chrominance component. The signaling of ALF parameters is removed from the slice / picture level to the CTU level. The calculation of the category index is performed at the 4x4 level instead of the 2x2 level. In addition, as proposed in JVET-L0147, a sub-sampled Laplacian calculation method for ALF classification is utilized. More specifically, there is no need to calculate the horizontal / vertical / 45 diagonal / 135 degree gradients for each sample point within a block. Instead, 1:2 subsampling is used.

[0216] 2.8 Nonlinear ALF in VVC

[0217] 2.8.1 Filtering and Reshaping

[0218] Equation 11 can be reformulated as follows without affecting the encoding and decoding efficiency:

[0219] O(x,y)=I(x,y)+∑ (i,j)≠(0,0) w(i,j).(I(x+i,y+j)-I(x,y)) (13)

[0220] where w(i,j) are the same filter coefficients as in equation (11) [except that w(0,0) is equal to 1 in equation (13) and 1-∑ (i,j)≠(0,0) w(i,j)].

[0221] Using filter formula 13, VVC introduces nonlinearity to make ALF more effective by using a simple clipping function to reduce the impact of the neighborhood sample value I(x+i,y+j)) being too different from the current sample value I(x,y) being filtered. More specifically, the ALF filter is modified as follows:

[0222] O′(x,y)=I(d,y)+∑ (i,j)≠(0,0) w(i,j).K(I(x+i,y+j)-I(d,x),k(i,j)) (14)

[0223] Where K(d,b)=min(b,max(-b,i)) is a clipping function and k(i,j) is a clipping parameter that depends on the (i,j) filter coefficients. The encoder performs an optimization to find the best k(i,j).

[0224] In an exemplary implementation, a clipping parameter k(i,j) is specified for each ALF filter, with one clipping value being signaled per filter coefficient. This means that up to 12 clipping values ​​can be signaled in the bitstream for each luma filter, and up to 6 clipping values ​​can be signaled for chroma filters. To limit signaling costs and encoder complexity, only 4 fixed values ​​are used, which are the same for INTER and INTRA slices.

[0225] Because the variance of local differences in luma is usually higher than the variance of local differences in chroma, two different sets of luma and chroma filters are applied. A maximum sample value in each set (here 1024 for a bit depth of 10 bits) is also introduced so that clipping can be disabled if not necessary. The set of clipping values ​​used in the exemplary implementation is provided in Table 5. These 4 values ​​are selected by roughly equally dividing the full range of sample values ​​for luma (encoded with 10 bits) and the range from 4 to 1024 for chroma in the logarithmic domain. More precisely, the luma table of clipping values ​​is obtained by the following formula:

[0226]

[0227] Similarly, the chromaticity table of the clipped value is obtained according to the following formula:

[0228]

[0229] INTRA / INTER slice group brightness {1024,181,32,6} Chroma {1024,161,25,4}

[0230] Table 5 Authorized limit values

[0231] The selected clipping value is encoded and decoded in the "alf_data" syntax element by using the Golomb coding scheme corresponding to the index of the clipping value in the above Table 5. This coding scheme is the same as the coding scheme of the filter index.

[0232] 2.9 Convolutional Neural Network-Based Loop Filters for Video Codecs

[0233] 2.9.1 Convolutional Neural Networks

[0234] In deep learning, convolutional neural networks (CNNs), also known as ConvNets, are a class of deep neural networks that can be applied to analyze visual images. They have been very successfully applied in image and video recognition / processing, recommender systems, image classification, medical image analysis, and natural language processing. CNNs are regularized versions of multilayer perceptrons. Multilayer perceptrons typically consist of fully connected networks, meaning that each neuron in one layer is connected to all neurons in the next layer. The "full connectivity" of these networks makes them prone to overfitting the data. Typical regularization methods involve adding some form of weight measurement to the loss function. CNNs take a different approach to regularization: they exploit hierarchical patterns in the data and assemble more complex patterns using smaller and simpler patterns. Therefore, on the scale of connectivity and complexity, CNNs are at the lower extreme.

[0235] Compared to other image classification / processing algorithms, CNNs use relatively little preprocessing. This means that the network learns filters that are hand-designed in other algorithms. This independence from prior knowledge and manual effort in feature design is a major advantage.

[0236] 2.9.2 Deep Learning for Image / Video Encoding and Decoding

[0237] Image / video compression based on deep learning may have two meanings: purely end-to-end compression based on neural networks and frameworks enhanced by neural networks. The first type can be implemented by convolutional neural networks or recurrent neural networks using a structure similar to an autoencoder. Although relying purely on neural networks for image / video compression can avoid any manual optimization or manual design, the compression efficiency may not be satisfactory. Therefore, the works distributed in the second type are assisted by neural networks and enhance the traditional compression framework by replacing or enhancing certain modules. In this way, they can inherit the advantages of highly optimized traditional frameworks. For example, in HEVC, one implementation can use a fully connected network for intra-frame prediction. In addition to intra-frame prediction, deep learning is also used to enhance other modules. For example, one implementation can replace the loop filter of HEVC with a convolutional neural network and obtain promising results. Another example applies neural networks to improve the arithmetic codec engine.

[0238] 2.9.3 Loop Filtering Based on Convolutional Neural Network

[0239] In lossy image / video compression, the reconstructed frame is an approximation of the original frame because the quantization process is irreversible and thus causes distortion in the reconstructed frame. To mitigate such distortion, a convolutional neural network can be trained to learn the mapping from the distorted frame to the original frame. In fact, training must be performed before deploying CNN-based loop filtering.

[0240] 2.9.3.1 Training

[0241] The purpose of the training process is to find the optimal values ​​of the parameters including weights and biases. First, a codec (e.g., HEVC test model (HM), JEM, VTM, etc.) is used to compress the training data set to generate distorted reconstructed frames. Then, the reconstructed frames are fed to the CNN, and the cost is calculated using the output of the CNN and the groundtruth frame (original frame). Common cost functions include the sum of absolute differences (SAD) and mean square error (MSE). Next, the gradient of the cost relative to each parameter is derived by the back propagation algorithm. Using the gradient, the parameter value can be updated. Repeat the above process until the convergence criterion is met. After completing the training, the derived optimal parameters are saved for the inference phase.

[0242] 2.9.3.2 Convolution Process

[0243] Fig.11 An exemplary CNN architecture is shown. M represents the number of feature maps. N represents the number of one-dimensional samples. (b) Construct the ResBlock in (a). During convolution, the filter moves from left to right and top to bottom across the image, where one pixel column changes when moving horizontally and one pixel row changes when moving vertically. The amount the filter moves across the input image is called the stride, and it is almost always symmetric in the height and width dimensions. The default stride in two dimensions is (1,1) for both height and width movement.

[0244] In most deep convolutional neural networks, residual blocks are used as basic modules and stacked several times to build the final network, where in one example, the residual block is obtained by combining a convolutional layer, a ReLU / PReLU activation function, and a convolutional layer, as shown in Fig.11 shown.

[0245] 2.9.3.3 Reasoning

[0246] In the inference phase, the distorted reconstructed frame is fed to the CNN and processed by the CNN model, whose parameters have been determined in the training phase. The input samples of the CNN can be the reconstructed samples before or after DB, or the reconstructed samples before or after SAO, or the reconstructed samples before or after ALF. The input samples may also include other auxiliary information decoded from the bitstream. For example, segmentation information, prediction information, residual information can be additionally fed into the CNN.

[0247] 3. Technical problems solved by public technical solutions

[0248] The exemplary neural network based codec tool has the following problem: No geometric transformation is applied to the input samples of the NN based codec tool. However, if a geometric transformation can be applied to the input of the neural network, it is possible to obtain a better representation in the latent domain.

[0249] 4. List of solutions and implementation examples

[0250] In order to solve the above problems, the following method is disclosed. The embodiments should be considered as examples to explain the general concept and should not be interpreted in a narrow way. In addition, these embodiments can be applied alone or in combination in any way.

[0251] One or more neural network (NN) models are trained as codec tools to improve the efficiency of video coding. These NN-based codec tools can be used to replace or enhance the modules involved in the video codec. For example, the NN model can be used as an additional intra-frame prediction mode, inter-frame prediction mode, transform kernel or loop filter. The present invention explains how to apply geometric transformations to the input samples and output samples of the NN model. It should be noted that the NN model can be used as any codec tool, such as NN-based intra-frame and / or inter-frame prediction, NN-based super-resolution, NN-based motion compensation, NN-based reference generation, NN-based fractional pixel interpolation, NN-based loop / post-filtering, etc. In the present disclosure, the NN model can be any kind of NN architecture, such as a convolutional neural network or a fully connected neural network, or a combination of a convolutional neural network and a fully connected neural network.

[0252] In the following discussion, a video unit may be a sequence, a picture, a slice, a tile, a sub-picture, a codec tree unit (CTU) and / or a codec tree block (CTB), a CTU and / or a CTB row, one or more codec units (CU) and / or codec blocks (CB), one or more CTUs and / or CTBs, one or more virtual pipe data units (VPDUs), a picture, a slice, a slice, and / or a sub-region within a tile. A parent video unit represents a unit that is larger than a video unit. Typically, a parent unit will contain several video units, for example, when the video unit is a CTU, the parent unit may be a slice, a CTU row, multiple CTUs, etc.

[0253] Example 1

[0254] In an example, a geometric transformation is applied to the input and / or output of the NN model. For example, a video unit (such as a picture, a stripe, a slice, and / or a block) having dimensions W×H (W and H refer to width and height, respectively) can be modified in a first manner before it is fed to a loop processing module or a post-processing module. The output video unit from the loop processing module or the post-processing module can be modified in a second manner before being used as a final output or as a reference picture.

[0255] Example 2

[0256] In one example, the loop processing module or the post-processing module may include at least one NN model. In the present disclosure, the loop processing module or the post-processing module may also be referred to as a NN model.

[0257] Example 3

[0258] In one example, the input and / or output of the NN model is video units.

[0259] Example 4

[0260] In one example, the modification to the video unit refers to one or more geometric transformations, such as reflection, rotation, flipping, and the like.

[0261] Example 5

[0262] In one example, assume that P(x,y) represents a video unit to be processed by the NN model, where x and y represent the horizontal and vertical coordinates of a sample in the video unit, and P represents the sample value (similar notation applies to the following examples). P'(x,y) = F(P(x,y)) can be fed into the NN model, where F is any function that can be applied to modify the video unit.

[0263] Example 6

[0264] In one example, assuming P(x,y) represents a video unit output from a NN model, P'(x,y)=G(P(x,y)) may be output and / or stored and / or used as a reference video unit, where G is any function that may be applied to modify the video unit.

[0265] Example 7

[0266] In one example, G should be the inverse operation of F, such as G(F(X))=X, where X is a picture.

[0267] Example 8

[0268] In one example, F and G may be flipped and / or rotated.

[0269] Example 9

[0270] In one example, the video unit is first flipped vertically, e.g. Fig.12 As shown, it is then fed into the NN model. The vertical flip is defined as:

[0271] P'(x,y)=P(x,H-1-y)

[0272] Example 10

[0273] In one example, the output video unit from the NN model is first flipped vertically, as Fig.12 As shown, it is then stored / used as a reference video unit. Vertical flip is defined in the equation of the above example.

[0274] Example 11

[0275] In one example, the video unit is first flipped horizontally, such as Fig.13 As shown, it is then fed into the NN model. The horizontal flip is defined as:

[0276] P'(x,y)=P(W-1-x,y)

[0277] Example 12

[0278] In one example, the output video unit from the NN model is first flipped horizontally, as Fig.13 As shown, it is then stored / used as a reference video unit. Horizontal flipping is defined in the equation of the above example.

[0279] Example 13

[0280] In one example, the video unit is first rotated 180 degrees (°), such as Fig.14 As shown, it is then fed to the NN model. A 180° rotation is defined as:

[0281] P'(x,y)=P(W-1-x,H-1-y)

[0282] Example 14

[0283] In one example, the output video unit from the NN model is first rotated 180°, as Fig.14 As shown, it is then stored / used as a reference video unit. The 180° rotation is defined in the equation of the above example.

[0284] Example 15

[0285] In one example, the video unit is first rotated 90° clockwise, as shown in FIG. Fig.15 As shown, it is then fed to the NN model. A 90° clockwise rotation is defined as:

[0286] P'(x,y)=P(height – y-1,x)

[0287] Example 16

[0288] In one example, the output video unit from the NN model is first rotated 90° clockwise, as Fig.15 As shown, it is then stored / used as a reference video unit. A 90° clockwise rotation is defined in the equation of the above example.

[0289] Example 17

[0290] In one example, the video unit is first rotated 270° clockwise, as shown in FIG. Fig.16 As shown, it is then fed to the NN model. A 270° clockwise rotation is defined as:

[0291] P'(x,y)=P(y,x)

[0292] Example 18

[0293] In one example, the output video unit from the NN model is first rotated 270° clockwise, as Fig.16 , and is then stored / used as a reference video unit. A 270° clockwise rotation is defined in the equation of the above example.

[0294] Example 19

[0295] In one example, the input to the NN model includes samples from both the current video unit and the adjacent video units, such as Fig.17 As shown (e.g., as an extended input block including samples from the current video unit and the adjacent video unit). The entire input block can be modified before being fed to the NN model. In one example, the entire input block, e.g. Fig.17 The grey area shown in can be flipped / rotated before being fed to the NN model.

[0296] Example 20

[0297] In one example, the padding points may be modified together with the existing points. In another example, the padding points may be filled after modification.

[0298] Example 21

[0299] In one example, derivation and / or signaling of geometric transformation types is employed. Whether and / or how to apply geometric transformation types to inputs and / or outputs of a NN model can be derived on the fly. In one example, whether and / or how to apply geometric transformation types to inputs and / or outputs of a NN model can be derived on the fly based on the content of a video unit.

[0300] In one example, whether and / or how to apply the geometric transformation type to the input and / or output of the NN model may depend on codec information such as picture and / or slice type, temporal layer, quantization parameter (QP), color format, color component, codec mode, dimension of video unit, etc. In one example, the geometric transformation is only applied to the NN model of inter slices. In one example, the geometric transformation is only applied to the NN model of the luma component.

[0301] Example 22

[0302] In one example, whether and / or how to apply a geometric transform to the input and / or output of the NN model may be signaled from the encoder to the decoder by at least one syntax element (SE), such as a sequence parameter set (SPS), a picture parameter set (PPS), an adaptation parameter set (APS), a picture header, a slice header, a CTU, a CU, etc. In one example, a first syntax element may be signaled to indicate whether a geometric transform is applied.

[0303] In one example, the second syntax element may be signaled to indicate which geometric transform is applied.The second syntax element may be signaled only if the first syntax indicates that a geometric transform is applied.

[0304] A single SE may be signaled. SE(s) may be coded using a fixed length codec, an exponential Golomb (EG) codec, a truncated (unary) codec, etc. SE(s) may be coded using at least one context in an arithmetic codec. SE(s) may be bypassed. SE(s) may be signaled only if modification is allowed.

[0305] Example 23

[0306] In one example, the processing module and / or NN model may be different for different modifications of the video unit. The processing module and / or NN model may be different depending on whether a modification is applied to the video unit.

[0307] Example 24

[0308] In one example, the processing module and / or NN model may be the same for different modifications of the video unit. The processing module and / or NN model may be the same regardless of whether a modification is applied to the video unit.

[0309] Example 27

[0310] In one example, whether and / or how to apply the above disclosed method can be signaled at the sequence level, picture group level, picture level, slice level and / or slice group level, such as in a sequence header, a picture header, an SPS, a video parameter set (VPS), a dependency parameter set (DPS), decoding capability information (DCI), a PPS, an APS, a slice header and / or a slice group header.

[0311] Example 28

[0312] In one example, whether and / or how to apply the above disclosed method may depend on codec information, such as block size, color format, single tree and / or dual tree partitioning, color component, slice and / or picture type, etc.

[0313] Example 28

[0314] In one example, the disclosed method can be applied to the input and / or output of any NN model for video coding, such as NN-based intra-frame and / or inter-frame prediction, NN-based super-resolution, NN-based motion compensation, NN-based reference generation, NN-based fractional pixel interpolation, NN-based loop / post filtering, etc. In one example, the disclosed method is applied to NN-based loop filtering.

[0315] Fig.18 4000. The system 4000 may include an input 4002 for receiving video content. The video content may be received in a raw or uncompressed format, such as 8-bit or 10-bit multi-component pixel values, or may be received in a compressed or encoded format. The input 4002 may represent a network interface, a peripheral bus interface, or a storage interface. Examples of network interfaces include wired interfaces such as Ethernet, a passive optical network (PON), and wireless interfaces such as Wi-Fi or a cellular interface.

[0316] System 4000 may include coding component 4004, which can implement various coding methods described in this document. Coding component 4004 can reduce the average bit rate of the video from input 4002 to the output of coding component 4004 to generate a coded representation of the video. Therefore, coding technology is sometimes referred to as video compression or video code conversion technology. The output of coding component 4004 can be stored, or sent via a connected communication (as represented by component 4006). Component 4008 can use the bit stream (or coding) representation of the storage or communication of the video received at input 4002 to generate pixel values ​​or displayable video sent to display interface 4010. The process of generating user-visible video from bit stream representation is sometimes referred to as video decompression. In addition, although some video processing operations are referred to as "coding" operations or tools, it should be understood that the coding tools or operations are used at the encoder, and the corresponding decoding tools or operations opposite to the coding results will be performed by the decoder.

[0317] Examples of peripheral bus interfaces or display interfaces may include Universal Serial Bus (USB) or High Definition Multimedia Interface (HDMI) or Display Port, etc. Examples of storage interfaces include Serial Advanced Technology Attachment (SATA), Peripheral Component Interconnect (PCI), Integrated Drive Electronics (IDE) interface, etc. The techniques described in this document may be embodied in various electronic devices, such as mobile phones, laptop computers, smart phones, or other devices capable of performing digital data processing and / or video display.

[0318] Fig.194106 is a block diagram of an exemplary video processing device 4100. Device 4100 can be used to implement one or more of the methods described herein. Device 4100 can be embodied in a smart phone, a tablet computer, a computer, an Internet of Things (IoT) receiver, etc. Device 4100 may include one or more processors 4102, one or more memories 4104, and video processing circuitry 4106. (Multiple) processors 4102 can be configured to implement one or more methods described in this document. (Multiple) memories 4104 can be used to store data and code for implementing the methods and techniques described herein. Video processing circuitry 4106 can be used to implement some of the techniques described in this document in hardware circuits. In some embodiments, video processing circuitry 4106 can be at least partially included in processor 4102, such as a graphics coprocessor.

[0319] Fig. 20 4200. The method 4200 includes determining, at step 4202, to modify a video unit in applying a video compression function. At step 4204, performing a conversion between visual media data and a bitstream based on the modified video unit. Depending on the example, the conversion of step 4204 may include encoding at an encoder or decoding at a decoder.

[0320] It should be noted that method 4200 may be implemented in an apparatus for processing video data, the apparatus comprising a processor and a non-transitory memory having instructions thereon, such as video encoder 4400, video decoder 4500, and / or encoder 4600. In such cases, the instructions, after being executed by the processor, cause the processor to perform method 4200. In addition, method 4200 may be performed by a non-transitory computer-readable medium including a computer program product for use by a video codec device. The computer program product includes computer-executable instructions stored on a non-transitory computer-readable medium, such that when executed by a processor, the video codec device performs method 4200.

[0321] Fig.21 43 is a block diagram illustrating an exemplary video codec system 4300 that can use the techniques of the present disclosure. The video codec system 4300 may include a source device 4310 and a target device 4320. The source device 4310 generates encoded video data and may be referred to as a video encoding device. The target device 4320 may decode the encoded video data generated by the source device 4310 and may be referred to as a video decoding device.

[0322] Source device 4310 may include video source 4312, video encoder 4314 and input / output (I / O) interface 4316. Video source 4312 may include sources such as video capture devices, interfaces for receiving video data from video content providers and / or computer graphics systems for generating video data, or a combination of such sources. Video data may include one or more pictures. Video encoder 4314 encodes video data from video source 4312 to generate a bitstream. The bitstream may include a sequence of bits forming a coded representation of video data. The bitstream may include coded pictures and associated data. The coded pictures are coded representations of pictures. Associated data may include sequence parameter sets, image parameter sets and other syntax structures. I / O interface 4316 may include a modulator / demodulator (modem) and / or a transmitter. The coded video data may be sent directly to target device 4320 via network 4330 via I / O interface 4316. The coded video data may also be stored on storage medium / server 4340 for access by target device 4320.

[0323] Target device 4320 may include an I / O interface 4326, a video decoder 4324, and a display device 4322. I / O interface 4326 may include a receiver and / or a modem. I / O interface 4326 may obtain encoded video data from source device 4310 or storage medium / server 4340. Video decoder 4324 may decode the encoded video data. Display device 4322 may display the decoded video data to a user. Display device 4322 may be integrated with target device 4320, or may be external to target device 4320, and target device 4320 may be configured to interface with an external display device.

[0324] The video encoder 4314 and the video decoder 4324 may operate according to a video compression standard, such as the High Efficiency Video Codec (HEVC) standard, the Versatile Video Codec (VVC) standard, and other current and / or further standards.

[0325] Fig. 22 is a block diagram showing an example of a video encoder 4400, which may be Fig.21 Video encoder 4314 in system 4300 shown. Video encoder 4400 can be configured to perform any or all of the techniques of the present disclosure. Video encoder 4400 includes multiple functional components. The techniques described in this disclosure can be shared between the various components of video encoder 4400. In some examples, the processor can be configured to perform any or all of the techniques described in this disclosure.

[0326] The functional components of the video encoder 4400 may include a segmentation unit 4401; a prediction unit 4402, which may include a mode selection unit 4403, a motion estimation unit 4404, a motion compensation unit 4405 and an intra-frame prediction unit 4406; a residual generation unit 4407; a transform processing unit 4408; a quantization unit 4409; an inverse quantization unit 4410; an inverse transform unit 4411; a reconstruction unit 4412; a buffer 4413; and an entropy coding unit 4414.

[0327] In other examples, the video encoder 4400 may include more, fewer, or different functional components. In an example, the prediction unit 4402 may include an intra-block copy (IBC) unit. The IBC unit may perform prediction in an IBC mode in which at least one reference picture is a picture in which the current video block is located.

[0328] Furthermore, some components, such as the motion estimation unit 4404 and the motion compensation unit 4405 , may be highly integrated but are represented separately in the example of the video encoder 4400 for purposes of explanation.

[0329] The segmentation unit 4401 may segment the picture into one or more video blocks. The video encoder 4400 and the video decoder 4500 may support various video block sizes.

[0330] The mode selection unit 4403 may select one of the coding modes (intra or inter) based on the error result, for example, and provide the resulting intra or inter coded block to the residual generation unit 4407 to generate residual block data, and to the reconstruction unit 4412 to reconstruct the coded block for use as a reference picture. In some examples, the mode selection unit 4403 may select a combined intra and inter prediction (CIIP) mode, where the prediction is based on an inter prediction signal and an intra prediction signal. In the case of inter prediction, the mode selection unit 4403 may also select a resolution of the motion vector for the block (e.g., sub-pixel or integer pixel precision).

[0331] In order to perform inter-frame prediction on the current video block, the motion estimation unit 4404 may generate motion information of the current video block by comparing one or more reference frames from the buffer 4413 with the current video block. The motion compensation unit 4405 may determine a predicted video block of the current video block based on the motion information of pictures other than the picture associated with the current video block from the buffer 4413 and decoded samples.

[0332] The motion estimation unit 4404 and the motion compensation unit 4405 may perform different operations on the current video block, for example, depending on whether the current video block is in an I slice, a P slice, or a B slice.

[0333] In some examples, the motion estimation unit 4404 may perform unidirectional prediction on the current video block, and the motion estimation unit 4404 may search for a reference video block of the current video block in the reference pictures of list 0 or list 1. The motion estimation unit 4404 may then generate a reference index indicating a reference picture in list 0 or list 1, the reference picture including the reference video block and a motion vector indicating a spatial displacement between the current video block and the reference video block. The motion estimation unit 4404 may output the reference index, the prediction direction indicator, and the motion vector as motion information of the current video block. The motion compensation unit 4405 may generate a predicted video block of the current block based on the reference video block indicated by the motion information of the current video block.

[0334] In other examples, the motion estimation unit 4404 may perform bidirectional prediction on the current video block, and the motion estimation unit 4404 may search for a reference video block of the current video block in the reference pictures in list 0, and may also search for another reference video block of the current video block in the reference pictures in list 1. The motion estimation unit 4404 may then generate a reference index and a motion vector, the reference index indicating the reference pictures in list 0 and list 1 including the reference video block, and the motion vector indicating the spatial displacement between the reference video block and the current video block. The motion estimation unit 4404 may output the reference index and the motion vector of the current video block as the motion information of the current video block. The motion compensation unit 4405 may generate a predicted video block of the current video block based on the reference video block indicated by the motion information of the current video block.

[0335] In some examples, motion estimation unit 4404 may output a full set of motion information for a decoding process of a decoder. In some examples, motion estimation unit 4404 may not output a full set of motion information for the current video. Instead, motion estimation unit 4404 may reference motion information of another video block to signal motion information of the current video block. For example, motion estimation unit 4404 may determine that the motion information of the current video block is sufficiently similar to the motion information of an adjacent video block.

[0336] In one example, the motion estimation unit 4404 may indicate a value in a syntax structure associated with the current video block that indicates to the video decoder 4500 that the current video block has the same motion information as another video block.

[0337] In another example, the motion estimation unit 4404 may identify another video block and a motion vector difference (MVD) in a syntax structure associated with the current video block. The motion vector difference indicates the difference between the motion vector of the current video block and the motion vector of the indicated video block. The video decoder 4500 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.

[0338] As described above, the video encoder 4400 may predictively signal motion vectors. Two examples of predictive signaling techniques that may be implemented by the video encoder 4400 include Advanced Motion Vector Prediction (AMVP) and merge mode signaling.

[0339] The intra prediction unit 4406 may perform intra prediction on the current video block. When the intra prediction unit 4406 performs intra prediction on the current video block, the intra prediction unit 4406 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.

[0340] The residual generating unit 4407 may generate residual data of the current video block by subtracting the predicted video block of the current video block from the current video block. The residual data of the current video block may include residual video blocks corresponding to different sample point components of the samples in the current video block.

[0341] In other examples, the current video block may not have residual data for the current video block, such as in skip mode, and the residual generation unit 4407 may not perform a subtraction operation.

[0342] The transform processing unit 4408 may generate one or more transform coefficient video blocks for the current video block by applying one or more transforms to the residual video block associated with the current video block.

[0343] After the transform processing unit 4408 generates a transform coefficient video block associated with the current video block, the quantization unit 4409 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.

[0344] The inverse quantization unit 4410 and the inverse transform unit 4411 may apply inverse quantization and inverse transform to the transform coefficient video block, respectively, to reconstruct a residual video block from the transform coefficient video block. The reconstruction unit 4412 may add the reconstructed residual video block to corresponding samples from one or more predicted video blocks generated by the prediction unit 4402 to generate a reconstructed video block associated with the current block for storage in the buffer 4413.

[0345] After the reconstruction unit 4412 reconstructs the video block, a loop filtering operation may be performed to reduce video block artifacts in the video block.

[0346] The entropy coding unit 4414 may receive data from other functional components of the video encoder 4400. When the entropy coding unit 4414 receives the data, the entropy coding unit 4414 may perform one or more entropy coding operations to generate entropy coded data, and output a bitstream including the entropy coded data.

[0347] Fig.23 is a block diagram showing an example of a video decoder 4500, which may be Fig.21 Video decoder 4324 in the system 4300 shown. Video decoder 4500 can be configured to perform any or all embodiments of the present disclosure. In the example shown, video decoder 4500 includes multiple functional components. The embodiments described in the present disclosure can be shared between various components of video decoder 4500. In some examples, the processor can be configured to perform any or all embodiments described in the present disclosure.

[0348] In the illustrated example, the video decoder 4500 includes an entropy decoding unit 4501, a motion compensation unit 4502, an intra prediction unit 4503, an inverse quantization unit 4504, an inverse transform unit 4505, a reconstruction unit 4506, and a buffer 4507. In some examples, the video decoder 4500 may perform a decoding process that is generally reciprocal to the encoding process described with reference to the video encoder 4400.

[0349] The entropy decoding unit 4501 may retrieve an encoded bitstream. The encoded bitstream may include entropy-encoded video data (e.g., encoded video data blocks). The entropy decoding unit 4501 may decode the entropy-encoded video data, and based on the entropy-decoded video data, the motion compensation unit 4502 may determine motion information including motion vectors, motion vector precision, reference picture list index, and other motion information. For example, the motion compensation unit 4502 may determine such information by performing AMVP and merge mode.

[0350] The motion compensation unit 4502 may generate a motion compensated block, possibly performing interpolation based on an interpolation filter. An identifier of an interpolation filter to be used with sub-pixel precision may be included in the syntax element.

[0351] The motion compensation unit 4502 may calculate interpolated values ​​of sub-integer pixels of the reference block using interpolation filters as used by the video encoder 4400 during encoding of the video block. The motion compensation unit 4502 may determine the interpolation filters used by the video encoder 4400 based on received syntax information and use the interpolation filters to generate a prediction block.

[0352] The motion compensation unit 4502 can use some syntax information to determine the size of the blocks used to encode (multiple) frames and / or (multiple) slices of the encoded video sequence, partitioning information describing how each macroblock of the pictures of the encoded video sequence is partitioned, a mode indicating how each partition is encoded, one or more reference frames (and reference frame lists) for each inter-frame codec block, and other information used to decode the encoded video sequence.

[0353] The intra prediction unit 4503 may form a prediction block from spatially neighboring blocks using, for example, an intra prediction mode received in the bitstream. The inverse quantization unit 4504 inversely quantizes (i.e., dequantizes) the quantized video block coefficients provided in the bitstream and decoded by the entropy decoding unit 4501. The inverse transform unit 4505 applies an inverse transform.

[0354] The reconstruction unit 4506 may add the residual block to the corresponding prediction block generated by the motion compensation unit 4502 or the intra prediction unit 4503 to form a decoded block. If necessary, a deblocking filter may also be applied to filter the decoded block to remove blocking artifacts. The decoded video block is then stored in a buffer 4507, which provides reference blocks for subsequent motion compensation / intra prediction and also generates a decoded video for presentation on a display device.

[0355] Fig.24 4600 is a schematic diagram of an exemplary encoder 4600. Encoder 4600 is suitable for implementing VVC technology. Encoder 4600 includes three loop filters, namely, a deblocking filter (DF) 4602, a sample adaptive offset (SAO) 4604, and an adaptive loop filter (ALF) 4606. Unlike DF 4602, which uses a predefined filter, SAO 4604 and ALF 4606 use the original samples of the current picture to reduce the mean square error between the original samples and the reconstructed samples by adding an offset and applying a finite impulse response (FIR) filter, respectively, where the auxiliary information of the codec signals the offset and the filter coefficients. ALF 4606 is located at the last processing stage of each picture and can be regarded as a tool that attempts to capture and repair artifacts generated by the previous stage.

[0356] The encoder 4600 also includes an intra prediction component 4608 and a motion estimation / compensation (ME / MC) component 4610 configured to receive an input video. The intra prediction component 4608 is configured to perform intra prediction, while the ME / MC component 4610 is configured to perform inter prediction using a reference picture obtained from a reference picture buffer 4612. The residual block from the inter prediction or intra prediction is fed to a transform (T) component 4614 and a quantization (Q) component 4616 to generate quantized residual transform coefficients, which are fed to an entropy coding component 4618. The entropy coding component 4618 entropy codes and decodes the prediction result and the quantized transform coefficients and sends them to a video decoder (not shown). The quantization component output from the quantization component 4616 can be fed to an inverse quantization (IQ) component 4620, an inverse transform component 4622, and a reconstruction (REC) component 4624. The REC component 4624 is capable of outputting images to the DF 4602, SAO 4604, and ALF 4606 for filtering before the images are stored in the reference picture buffer 4612.

[0357] A list of some example preferred solutions is provided next.

[0358] The following solutions present examples of the embodiments discussed herein.

[0359] 1. A method for processing video data (e.g., Fig. 20 The method 4200 depicted in the claims includes: determining (4202) to modify a video unit in the process of applying a video compression function; and performing (4204) conversion between visual media data and a bitstream based on the modified video unit.

[0360] 2. The method according to solution 1, wherein the video unit is modified before applying an encoding function of a video compression function or after applying a decoding function of a video compression function.

[0361] 3. A method according to any of solutions 1-2, wherein the video compression function includes at least one neural network (NN) module.

[0362] 4. The method according to any of solutions 1-3, wherein the modification comprises applying one or more geometric transformations to the video unit.

[0363] 5. The method according to any of solutions 1-4, wherein the modification comprises applying the following function: P'(x,y)=F(P(x,y)), wherein P(x,y) is a video unit, F() is an encoding modification function, and P'(x,y) is a modified video unit.

[0364] 6. The method according to any of solutions 1-5, wherein the modification comprises applying the following function: P'(x,y)=G(P(x,y)), wherein P(x,y) is a video unit, G() is a decoding modification function, and P'(x,y) is a modified video unit.

[0365] 7. A method according to any one of solutions 1-6, wherein the modification includes vertically flipping the video unit according to the following formula: P'(x,y) = P(x,H-1-y), where P(x,y) is the video unit, H is the height of the video unit, and P'(x,y) is the modified video unit.

[0366] 8. A method according to any of solutions 1-6, wherein the modification includes horizontally flipping the video unit according to the following formula: P'(x,y) = P(W-1-x,y), where P(x,y) is the video unit, W is the width of the video unit, and P'(x,y) is the modified video unit.

[0367] 9. A method according to any one of solutions 1-6, wherein the modification includes rotating the video unit 180 degrees according to the following formula: P'(x,y) = P(W-1-x,H-1-y), wherein P(x,y) is the video unit, W is the width of the video unit, H is the height of the video unit, and P'(x,y) is the modified video unit.

[0368] 10. A method according to any one of solutions 1-6, wherein the modification includes rotating the video unit 90 degrees according to the following formula: P'(x,y) = P(H-y-1,x), where P(x,y) is the video unit, H is the height of the video unit, and P'(x,y) is the modified video unit.

[0369] 11. A method according to any of solutions 1-6, wherein the modification comprises rotating the video unit 270 degrees according to the following formula: P'(x,y) = P(y,x), where P(x,y) is the video unit, and P'(x,y) is the modified video unit.

[0370] 12. The method according to any of the solutions 1-11, wherein the modifying comprises modifying samples of the video unit and neighboring video units.

[0371] 13. The method according to any of the solutions 1-12, wherein determining the modification is derived based on content in the video unit.

[0372] 14. The method according to any of the solutions 1-12, wherein determining the modification is derived based on codec information related to the video unit.

[0373] 15. The method according to any of solutions 1-12, wherein determining the modification is derived based on syntax elements included in the bitstream.

[0374] 16. The method according to any of solutions 1-12, wherein determining the modification function is derived based on syntax elements included in the bitstream.

[0375] 17. A method according to any one of solutions 1-12, wherein the syntax elements related to the modification are included in a sequence header, a picture header, a sequence parameter set (SPS), a video parameter set (VPS), a dependency parameter set (DPS), decoding capability information (DCI), a picture parameter set (PPS), an adaptation parameter set (PPS), a slice header, a slice group header or a combination thereof.

[0376] 18. The method according to any one of solutions 1-12, determining the modification is derived based on block size, color format, single tree and / or dual tree partitioning, color component, slice type, picture type, or a combination thereof.

[0377] 19. A method according to any one of solutions 1-18, wherein the video compression function performs conversion based on the modified video unit, and wherein the video compression function adopts neural network (NN) based inter-frame prediction, NN based intra-frame prediction, NN based super-resolution, NN based motion compensation, NN based reference generation, NN based fractional pixel interpolation, NN based loop filtering, NN based post-loop filtering or a combination thereof.

[0378] 20. An apparatus for processing video data comprising: a processor; and a non-transitory memory having instructions thereon, wherein the instructions, when executed by the processor, cause the processor to perform the method of any one of solutions 1-19.

[0379] 21. A non-transitory computer-readable medium, comprising a computer program product for use by a video codec device, the computer program product comprising computer executable instructions stored on the non-transitory computer-readable medium, so that when executed by a processor, the video codec device performs the method of any one of solutions 1-19.

[0380] 22. A non-transitory computer-readable recording medium storing a bitstream of a video generated by a method performed by a video processing device, wherein the method comprises: determining that a video unit is modified in the process of applying a video compression function; and generating a bitstream based on the determination.

[0381] 23. A method for storing a bitstream of a video, comprising: determining that a video unit is modified in the process of applying a video compression function; generating a bitstream based on the determination; and storing the bitstream in a non-transitory computer-readable recording medium.

[0382] 24. A method, apparatus or system is described in this document.

[0383] In the solution described herein, an encoder can comply with the format rules by generating a codec representation according to the format rules. In the solution described herein, a decoder can use the format rules to parse syntax elements in the coded representation, understand the presence and absence of syntax elements according to the format rules, and generate decoded video.

[0384] In this document, the term "video processing" may refer to video encoding, video decoding, video compression, or video decompression. For example, during the conversion from a pixel representation of a video to a corresponding bitstream representation, a video compression algorithm may be applied, or vice versa. As defined by the syntax, the bitstream representation of the current video block may correspond, for example, to bits that are co-located or dispersed at different locations within the bitstream. For example, a macroblock may be encoded based on a transformed and encoded error residual value, and also using bits in a header and other fields in the bitstream. In addition, during the conversion, the decoder may parse the bitstream based on this determination, knowing that some fields may or may not be present, as described in the above solution. Similarly, the encoder may determine whether to include or not include certain syntax fields, and generate the codec representation accordingly by including or excluding the syntax fields in the codec representation.

[0385] The disclosed and other solutions, examples, embodiments, modules and functional operations described in this document may be implemented in digital electronic circuits, or in computer software, firmware or hardware, including the structures disclosed in this document and their structural equivalents, or in a combination of one or more of them. The disclosed and other embodiments may be implemented as one or more computer program products, i.e., one or more modules of computer program instructions encoded on a computer-readable medium, for execution by a data processing device or for controlling the operation of the data processing device. The computer-readable medium may be a machine-readable storage device, a machine-readable storage substrate, a memory device, a material combination that implements a machine-readable propagation signal, or a combination of one or more of them. The term "data processing device" includes all devices, equipment and machines for processing data, including, for example, a programmable processor, a computer or multiple processors or computers. In addition to hardware, the device may include code that creates an execution environment for the computer program in question, such as code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them. A propagation signal is an artificially generated signal, such as a machine-generated electrical, optical or electromagnetic signal, which is generated to encode information for transmission to a suitable receiver device.

[0386] A computer program (also referred to as a program, software, software application, script, or code) may be written in any form of programming language, including compiled or interpreted languages, and it may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program may be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing portions of one or more modules, subroutines, or code). A computer program may be deployed to execute on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.

[0387] The processes and logic flows described in this document can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by special purpose logic circuits, and the apparatus can also be implemented as special purpose logic circuits, such as field programmable gate arrays (FPGAs) or application specific integrated circuits (ASICs).

[0388] Processors suitable for executing computer programs include, for example, general-purpose and special-purpose microprocessors and any one or more processors of any kind of digital computer. Typically, the processor will receive instructions and data from a read-only memory or a random access memory or both. The basic elements of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices (e.g., magnetic disks, magneto-optical disks, or optical disks) for storing data, or be coupled in an operational manner to receive data from one or more mass storage devices or to transmit data to one or more mass storage devices or both. However, a computer need not have such devices. Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including, for example: semiconductor memory devices, such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and flash memory devices; magnetic disks, such as internal hard disks or removable disks; magneto-optical disks; and compact disc read-only memory (CD ROM) and digital versatile disc read-only memory (DVD-ROM) disks. The processor and memory can be supplemented by or incorporated into a dedicated logic circuit.

[0389] Although the present disclosure contains many details, these should not be understood as limitations on any subject matter or the scope that may be claimed, but rather as descriptions of features peculiar to specific embodiments of specific technologies. Certain features described in the context of separate embodiments of the present disclosure may also be implemented in combination in a single embodiment. On the contrary, the various features described in the context of a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may be described above as working in certain combinations and even initially claimed as such, in some cases, one or more features may be deleted from the claimed combination, and the claimed combination may involve a variant of a sub-combination or a sub-combination.

[0390] Similarly, although operations are depicted in a particular order in the figures, this should not be understood as requiring that such operations be performed in the particular order shown or in a sequential order, or that all of the illustrated operations be performed, in order to achieve the desired results. Furthermore, the separation of various system components in the embodiments described in this disclosure should not be understood as requiring such separation in all embodiments.

[0391] Only a few implementations and examples are described, and other implementations, enhancements, and variations may be made based on what is described and illustrated in this disclosure.

[0392] A first component is directly coupled to a second component when there are no intermediate components other than a line, trace, or another medium between the first and second components. A first component is indirectly coupled to a second component when there are intermediate components other than a line, trace, or another medium between the first and second components. The term "coupled" and variations thereof include both direct and indirect couplings. Unless otherwise indicated, use of the term "about" is intended to include a range of ±10% of the subsequent numerical value.

[0393] Although several embodiments have been provided in the present disclosure, it should be understood that the disclosed systems and methods may be embodied in many other specific forms without departing from the spirit or scope of the present disclosure. The present examples are considered to be illustrative rather than restrictive, and are not intended to be limited to the details given herein. For example, various elements or components may be combined or integrated in another system, or certain features may be omitted or not implemented.

[0394] In addition, without departing from the scope of the present disclosure, the techniques, systems, subsystems, and methods described and shown as discrete or independent in various embodiments may be combined or integrated with other systems, modules, techniques, or methods. Other items shown or discussed as coupled may be directly connected, or may be indirectly coupled or communicated electrically, mechanically, or otherwise through some interface, device, or intermediate component. Other examples of changes, substitutions, and alterations may be determined by those skilled in the art, and these changes, substitutions, and alterations may be made without departing from the spirit and scope disclosed herein.

Claims

1. A method for processing video data, comprising: Determining that video units are modified during the process of applying a video compression function; as well as Conversion between visual media data and a bitstream is performed based on the modified video unit.

2. The method according to claim 1, wherein: The video unit is modified before applying an encoding function of the video compression function or after applying a decoding function of the video compression function.

3. The method according to claim 1 or 2, wherein The video compression function includes at least one neural network (NN) module.

4. The method according to any one of claims 1 to 3, wherein: The video unit is modified by applying one or more geometric transforms to the video unit.

5. The method according to any one of claims 1 to 4, wherein: The video unit is modified by applying the following function: P'(x,y)=F(P(x,y)), Wherein P(x, y) is the video unit, F() is the encoding modification function, and P'(x, y) is the modified video unit.

6. The method according to any one of claims 1 to 5, wherein: The video unit is modified by applying the following function: P'(x,y)=G(P(x,y)), Wherein P(x, y) is the video unit, G() is a decoding modification function, and P'(x, y) is the modified video unit.

7. The method according to any one of claims 1 to 6, wherein: The video unit is modified by flipping the video unit vertically according to the following formula: P'(x,y)=P(x,H-1-y), Wherein P(x, y) is the video unit, H is the height of the video unit, and P'(x, y) is the modified video unit.

8. The method according to any one of claims 1 to 6, wherein: The video unit is modified by flipping the video unit horizontally according to the following formula: P'(x,y)=P(W-1-x,y), Wherein P(x, y) is the video unit, W is the width of the video unit, and P'(x, y) is the modified video unit.

9. The method according to any one of claims 1 to 6, wherein: The video unit is modified by rotating the video unit 180 degrees according to the following formula: P'(x,y)=P(W-1-x,H-1-y), Wherein P(x, y) is the video unit, W is the width of the video unit, H is the height of the video unit, and P'(x, y) is the modified video unit.

10. The method according to any one of claims 1 to 6, wherein: The video unit is modified by rotating the video unit 90 degrees according to the following formula: P'(x,y)=P(H–y-1,x), Wherein P(x, y) is the video unit, H is the height of the video unit, and P'(x, y) is the modified video unit.

11. The method according to any one of claims 1 to 6, wherein: The video unit is modified by rotating the video unit 270 degrees according to the following formula: P'(x,y)=P(y,x), Wherein P(x,y) is the video unit, and P'(x,y) is the modified video unit.

12. The method according to any one of claims 1-11, further comprising modifying samples of the video unit and neighboring video units.

13. The method according to any one of claims 1 to 12, wherein: The determined modification is derived based on content in the video unit.

14. The method according to any one of claims 1 to 12, wherein: The determined modification is derived based on codec information associated with the video unit.

15. The method according to any one of claims 1 to 12, wherein: The determined modification is derived based on syntax elements included in the bitstream.

16. The method according to any of claims 1-12, further comprising determining a modification function based on syntax elements contained in the bitstream.

17. The method according to any one of claims 1 to 12, wherein: The syntax elements related to the modification are included in a sequence header, a picture header, a sequence parameter set (SPS), a video parameter set (VPS), a dependency parameter set (DPS), decoding capability information (DCI), a picture parameter set (PPS), an adaptation parameter set (PPS), a slice header, a slice group header, or a combination thereof.

18. The method according to any one of claims 1 to 12, wherein: The determination modification is derived based on block size, color format, single tree and / or dual tree partitioning, color component, slice type, picture type, or a combination thereof.

19. The method according to any one of claims 1 to 18, wherein: The video compression function performs the conversion based on the modified video unit, and wherein the video compression function adopts neural network (NN) based inter-frame prediction, NN based intra-frame prediction, NN based super-resolution, NN based motion compensation, NN based reference generation, NN based fractional pixel interpolation, NN based loop filtering, NN based post-loop filtering or a combination thereof.

20. An apparatus for processing video data, comprising: processor; as well as A non-transitory memory coupled to the processor and having instructions thereon, wherein the instructions, when executed by the processor, cause the processor to perform the method according to any one of claims 1-19.

21. A non-transitory computer-readable medium, comprising a computer program product for use by a video codec device, the computer program product comprising computer executable instructions stored on the non-transitory computer-readable medium, so that when executed by a processor, the video codec device performs the method according to any one of claims 1-19.

22. A non-transitory computer-readable recording medium storing a bit stream of a video generated by a method executed by a video processing device, wherein: The method comprises: Determining that video units are modified in the process of applying a video compression function; and The bitstream is generated based on the determination.

23. A method for storing a bit stream of a video, comprising: Determining that video units are modified during the process of applying a video compression function; generating the bitstream based on the determination; as well as The bit stream is stored in a non-transitory computer-readable recording medium.

Images