WO2024061136A1

WO2024061136A1 - Method, apparatus, and medium for video processing

Info

Publication number: WO2024061136A1
Application number: PCT/CN2023/119227
Authority: WO
Inventors: Chaoyi Lin; Ye-Kui Wang; Kai Zhang; Li Zhang; Yue Li; Junru LI
Original assignee: Douyin Vision Co., Ltd.; Bytedance Inc.
Priority date: 2022-09-19
Filing date: 2023-09-15
Publication date: 2024-03-28

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: performing a conversion between a current video unit of a video and a bitstream of the video, wherein the bitstream comprises information of a downsampling filter for obtaining the current video unit.

Description

METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING

FIELDS

Embodiments of the present disclosure relates generally to video processing techniques, and more particularly, to neural-network post-filter with downsampling information.

BACKGROUND

In nowadays, digital video capabilities are being applied in various aspects of peoples’ lives. Multiple types of video compression technologies, such as MPEG-2, MPEG-4, ITU-TH. 263, ITU-TH. 264/MPEG-4 Part 10 Advanced Video Coding (AVC) , ITU-TH. 265 high efficiency video coding (HEVC) standard, versatile video coding (VVC) standard, have been proposed for video encoding/decoding. However, coding quality of video coding techniques is generally expected to be further improved.

SUMMARY

Embodiments of the present disclosure provide a solution for video processing.

In a first aspect, a method for video processing is proposed. The method comprises: performing a conversion between a current video unit of a video and a bitstream of the video, wherein the bitstream comprises information of a downsampling filter for obtaining the current video unit.

According to the method in accordance with the first aspect of the present disclosure, the information of the downsampling filter for obtaining the current video unit is signaled in the bitstream. Compared with the conventional solution, where such information is not signaled, the proposed method can advantageously enable an optimization of a post-processing filter for quality improvement based on the information of the downsampling filter, and thus the quality of the video after post-processing can be improved.

In a second aspect, an apparatus for video processing is proposed. The apparatus comprises a processor and a non-transitory memory with instructions thereon. The instructions upon execution by the processor, cause the processor to perform a method in accordance with the first aspect of the present disclosure.

In a third aspect, a non-transitory computer-readable storage medium is proposed. The non-transitory computer-readable storage medium stores instructions that cause a processor to perform a method in accordance with the first aspect of the present disclosure.

In a fourth aspect, another non-transitory computer-readable recording medium is proposed. The non-transitory computer-readable recording medium stores a bitstream of a video which is generated by a method performed by an apparatus for video processing. The method comprises: performing a conversion between a current video unit of the video and the bitstream, wherein the bitstream comprises information of a downsampling filter for obtaining the current video unit.

In a fifth aspect, a method for storing a bitstream of a video is proposed. The method comprises: performing a conversion between a current video unit of the video and the bitstream, wherein the bitstream comprises information of a downsampling filter for obtaining the current video unit; and storing the bitstream in a non-transitory computer-readable recording medium.

This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

BRIEF DESCRIPTION OF THE DRAWINGS

Through the following detailed description with reference to the accompanying drawings, the above and other objectives, features, and advantages of example embodiments of the present disclosure will become more apparent. In the example embodiments of the present disclosure, the same reference numerals usually refer to the same components.

Fig. 1 illustrates a block diagram that illustrates an example video coding system, in accordance with some embodiments of the present disclosure;

Fig. 2 illustrates a block diagram that illustrates a first example video encoder, in accordance with some embodiments of the present disclosure;

Fig. 3 illustrates a block diagram that illustrates an example video decoder, in accordance with some embodiments of the present disclosure;

Fig. 4 is an example illustration of luma data channels;

Fig. 5 illustrates a flowchart of a method for video processing in accordance with embodiments of the present disclosure; and

Fig. 6 illustrates a block diagram of a computing device in which various embodiments of the present disclosure can be implemented.

Throughout the drawings, the same or similar reference numerals usually refer to the same or similar elements.

DETAILED DESCRIPTION

Principle of the present disclosure will now be described with reference to some embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. The disclosure described herein can be implemented in various manners other than the ones described below.

In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

References in the present disclosure to “one embodiment, ” “an embodiment, ” “an example embodiment, ” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an example embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

It shall be understood that although the terms “first” and “second” etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and/or” includes any and all combinations of one or more of the listed terms.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a” , “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” , “comprising” , “has” , “having” , “includes” and/or “including” , when used herein, specify the presence of stated features, elements, and/or components etc., but do not preclude the presence or addition of one or more other features, elements, components and/or combinations thereof.

Example Environment

Fig. 1 is a block diagram that illustrates an example video coding system 100 that may utilize the techniques of this disclosure. As shown, the video coding system 100 may include a source device 110 and a destination device 120. The source device 110 can be also referred to as a video encoding device, and the destination device 120 can be also referred to as a video decoding device. In operation, the source device 110 can be configured to generate encoded video data and the destination device 120 can be configured to decode the encoded video data generated by the source device 110. The source device 110 may include a video source 112, a video encoder 114, and an input/output (I/O) interface 116.

The video source 112 may include a source such as a video capture device. Examples of the video capture device include, but are not limited to, an interface to receive video data from a video content provider, a computer graphics system for generating video data, and/or a combination thereof.

The video data may comprise one or more pictures. The video encoder 114 encodes the video data from the video source 112 to generate a bitstream. The bitstream may include a sequence of bits that form a coded representation of the video data. The bitstream may include coded pictures and associated data. The coded picture is a coded representation of a picture. The associated data may include sequence parameter sets, picture parameter sets, and other syntax structures. The I/O interface 116 may include a modulator/demodulator and/or a transmitter. The encoded video data may be transmitted directly to destination device 120 via the I/O interface 116 through the network 130A. The encoded video data may also be stored onto a storage medium/server 130B for access by destination device 120.

The destination device 120 may include an I/O interface 126, a video decoder 124, and a display device 122. The I/O interface 126 may include a receiver and/or a modem. The I/O interface 126 may acquire encoded video data from the source device 110 or the storage medium/server 130B. The video decoder 124 may decode the encoded video data. The display device 122 may display the decoded video data to a user. The display device 122 may be integrated with the destination device 120, or may be external to the destination device 120 which is configured to interface with an external display device.

The video encoder 114 and the video decoder 124 may operate according to a video compression standard, such as the High Efficiency Video Coding (HEVC) standard, Versatile Video Coding (VVC) standard and other current and/or further standards.

Fig. 2 is a block diagram illustrating an example of a video encoder 200, which may be an example of the video encoder 114 in the system 100 illustrated in Fig. 1, in accordance with some embodiments of the present disclosure.

The video encoder 200 may be configured to implement any or all of the techniques of this disclosure. In the example of Fig. 2, the video encoder 200 includes a plurality of functional components. The techniques described in this disclosure may be shared among the various components of the video encoder 200. In some examples, a processor may be configured to perform any or all of the techniques described in this disclosure.

In some embodiments, the video encoder 200 may include a partition unit 201, a predication unit 202 which may include a mode select unit 203, a motion estimation unit 204, a motion compensation unit 205 and an intra-prediction unit 206, a residual generation unit 207, a transform unit 208, a quantization unit 209, an inverse quantization unit 210, an inverse transform unit 211, a reconstruction unit 212, a buffer 213, and an entropy encoding unit 214.

In other examples, the video encoder 200 may include more, fewer, or different functional components. In an example, the predication unit 202 may include an intra block copy (IBC) unit. The IBC unit may perform predication in an IBC mode in which at least one reference picture is a picture where the current video block is located.

Furthermore, although some components, such as the motion estimation unit 204 and the motion compensation unit 205, may be integrated, but are represented in the example of Fig. 2 separately for purposes of explanation.

The partition unit 201 may partition a picture into one or more video blocks. The video encoder 200 and the video decoder 300 may support various video block sizes.

The mode select unit 203 may select one of the coding modes, intra or inter, e.g., based on error results, and provide the resulting intra-coded or inter-coded block to a residual generation unit 207 to generate residual block data and to a reconstruction unit 212 to reconstruct the encoded block for use as a reference picture. In some examples, the mode select unit 203 may select a combination of intra and inter predication (CIIP) mode in which the predication is based on an inter predication signal and an intra predication signal. The mode select unit 203 may also select a resolution for a motion vector (e.g., a sub-pixel or integer pixel precision) for the block in the case of inter-predication.

To perform inter prediction on a current video block, the motion estimation unit 204 may generate motion information for the current video block by comparing one or more reference frames from buffer 213 to the current video block. The motion compensation unit 205 may determine a predicted video block for the current video block based on the motion information and decoded samples of pictures from the buffer 213 other than the picture associated with the current video block.

The motion estimation unit 204 and the motion compensation unit 205 may perform different operations for a current video block, for example, depending on whether the current video block is in an I-slice, a P-slice, or a B-slice. As used herein, an “I-slice” may refer to a portion of a picture composed of macroblocks, all of which are based upon macroblocks within the same picture. Further, as used herein, in some aspects, “P-slices” and “B-slices” may refer to portions of a picture composed of macroblocks that are not dependent on macroblocks in the same picture.

In some examples, the motion estimation unit 204 may perform uni-directional prediction for the current video block, and the motion estimation unit 204 may search reference pictures of list 0 or list 1 for a reference video block for the current video block. The motion estimation unit 204 may then generate a reference index that indicates the reference picture in list 0 or list 1 that contains the reference video block and a motion vector that indicates a spatial displacement between the current video block and the reference video block. The motion estimation unit 204 may output the reference index, a prediction direction indicator, and the motion vector as the motion information of the current video block. The motion compensation unit 205 may generate the predicted video block of the current video block based on the reference video block indicated by the motion information of the current video block.

Alternatively, in other examples, the motion estimation unit 204 may perform bi-directional prediction for the current video block. The motion estimation unit 204 may search the reference pictures in list 0 for a reference video block for the current video block and may also search the reference pictures in list 1 for another reference video block for the current video block. The motion estimation unit 204 may then generate reference indexes that indicate the reference pictures in list 0 and list 1 containing the reference video blocks and motion vectors that indicate spatial displacements between the reference video blocks and the current video block. The motion estimation unit 204 may output the reference indexes and the motion vectors of the current video block as the motion information of the current video block. The motion compensation unit 205 may generate the predicted video block of the current video block based on the reference video blocks indicated by the motion information of the current video block.

In some examples, the motion estimation unit 204 may output a full set of motion information for decoding processing of a decoder. Alternatively, in some embodiments, the motion estimation unit 204 may signal the motion information of the current video block with reference to the motion information of another video block. For example, the motion estimation unit 204 may determine that the motion information of the current video block is sufficiently similar to the motion information of a neighboring video block.

In one example, the motion estimation unit 204 may indicate, in a syntax structure associated with the current video block, a value that indicates to the video decoder 300 that the current video block has the same motion information as the another video block.

In another example, the motion estimation unit 204 may identify, in a syntax structure associated with the current video block, another video block and a motion vector difference (MVD) . The motion vector difference indicates a difference between the motion vector of the current video block and the motion vector of the indicated video block. The video decoder 300 may use the motion vector of the indicated video block and the motion vector difference to determine the motion vector of the current video block.

As discussed above, video encoder 200 may predictively signal the motion vector. Two examples of predictive signaling techniques that may be implemented by video encoder 200 include advanced motion vector predication (AMVP) and merge mode signaling.

The intra prediction unit 206 may perform intra prediction on the current video block. When the intra prediction unit 206 performs intra prediction on the current video block, the intra prediction unit 206 may generate prediction data for the current video block based on decoded samples of other video blocks in the same picture. The prediction data for the current video block may include a predicted video block and various syntax elements.

The residual generation unit 207 may generate residual data for the current video block by subtracting (e.g., indicated by the minus sign) the predicted video block (s) of the current video block from the current video block. The residual data of the current video block may include residual video blocks that correspond to different sample components of the samples in the current video block.

In other examples, there may be no residual data for the current video block for the current video block, for example in a skip mode, and the residual generation unit 207 may not perform the subtracting operation.

The transform processing unit 208 may generate one or more transform coefficient video blocks for the current video block by applying one or more transforms to a residual video block associated with the current video block.

After the transform processing unit 208 generates a transform coefficient video block associated with the current video block, the quantization unit 209 may quantize the transform coefficient video block associated with the current video block based on one or more quantization parameter (QP) values associated with the current video block.

The inverse quantization unit 210 and the inverse transform unit 211 may apply inverse quantization and inverse transforms to the transform coefficient video block, respectively, to reconstruct a residual video block from the transform coefficient video block. The reconstruction unit 212 may add the reconstructed residual video block to corresponding samples from one or more predicted video blocks generated by the predication unit 202 to produce a reconstructed video block associated with the current video block for storage in the buffer 213.

After the reconstruction unit 212 reconstructs the video block, loop filtering operation may be performed to reduce video blocking artifacts in the video block.

The entropy encoding unit 214 may receive data from other functional components of the video encoder 200. When the entropy encoding unit 214 receives the data, the entropy encoding unit 214 may perform one or more entropy encoding operations to generate entropy encoded data and output a bitstream that includes the entropy encoded data.

Fig. 3 is a block diagram illustrating an example of a video decoder 300, which may be an example of the video decoder 124 in the system 100 illustrated in Fig. 1, in accordance with some embodiments of the present disclosure.

The video decoder 300 may be configured to perform any or all of the techniques of this disclosure. In the example of Fig. 3, the video decoder 300 includes a plurality of functional components. The techniques described in this disclosure may be shared among the various components of the video decoder 300. In some examples, a processor may be configured to perform any or all of the techniques described in this disclosure.

In the example of Fig. 3, the video decoder 300 includes an entropy decoding unit 301, a motion compensation unit 302, an intra prediction unit 303, an inverse quantization unit 304, an inverse transformation unit 305, and a reconstruction unit 306 and a buffer 307. The video decoder 300 may, in some examples, perform a decoding pass generally reciprocal to the encoding pass described with respect to video encoder 200.

The entropy decoding unit 301 may retrieve an encoded bitstream. The encoded bitstream may include entropy coded video data (e.g., encoded blocks of video data) . The entropy decoding unit 301 may decode the entropy coded video data, and from the entropy decoded video data, the motion compensation unit 302 may determine motion information including motion vectors, motion vector precision, reference picture list indexes, and other motion information. The motion compensation unit 302 may, for example, determine such information by performing the AMVP and merge mode. AMVP is used, including derivation of several most probable candidates based on data from adjacent PBs and the reference picture. Motion information typically includes the horizontal and vertical motion vector displacement values, one or two reference picture indices, and, in the case of prediction regions in B slices, an identification of which reference picture list is associated with each index. As used herein, in some aspects, a “merge mode” may refer to deriving the motion information from spatially or temporally neighboring blocks.

The motion compensation unit 302 may produce motion compensated blocks, possibly performing interpolation based on interpolation filters. Identifiers for interpolation filters to be used with sub-pixel precision may be included in the syntax elements.

The motion compensation unit 302 may use the interpolation filters as used by the video encoder 200 during encoding of the video block to calculate interpolated values for sub-integer pixels of a reference block. The motion compensation unit 302 may determine the interpolation filters used by the video encoder 200 according to the received syntax information and use the interpolation filters to produce predictive blocks.

The motion compensation unit 302 may use at least part of the syntax information to determine sizes of blocks used to encode frame (s) and/or slice (s) of the encoded video sequence, partition information that describes how each macroblock of a picture of the encoded video sequence is partitioned, modes indicating how each partition is encoded, one or more reference frames (and reference frame lists) for each inter-encoded block, and other information to decode the encoded video sequence. As used herein, in some aspects, a “slice” may refer to a data structure that can be decoded independently from other slices of the same picture, in terms of entropy coding, signal prediction, and residual signal reconstruction. A slice can either be an entire picture or a region of a picture.

The intra prediction unit 303 may use intra prediction modes for example received in the bitstream to form a prediction block from spatially adjacent blocks. The inverse quantization unit 304 inverse quantizes, i.e., de-quantizes, the quantized video block coefficients provided in the bitstream and decoded by entropy decoding unit 301. The inverse transform unit 305 applies an inverse transform.

The reconstruction unit 306 may obtain the decoded blocks, e.g., by summing the residual blocks with the corresponding prediction blocks generated by the motion compensation unit 302 or intra-prediction unit 303. If desired, a deblocking filter may also be applied to filter the decoded blocks in order to remove blockiness artifacts. The decoded video blocks are then stored in the buffer 307, which provides reference blocks for subsequent motion compensation/intra predication and also produces decoded video for presentation on a display device.

Some exemplary embodiments of the present disclosure will be described in detailed hereinafter. It should be understood that section headings are used in the present document to facilitate ease of understanding and do not limit the embodiments disclosed in a section to only that section. Furthermore, while certain embodiments are described with reference to Versatile Video Coding or other specific video codecs, the disclosed techniques are applicable to other video coding technologies also. Furthermore, while some embodiments describe video coding steps in detail, it will be understood that corresponding steps decoding that undo the coding will be implemented by a decoder. Furthermore, the term video processing encompasses video coding or compression, video decoding or decompression and video transcoding in which video pixels are represented from one compressed format into another compressed format or at a different compressed bitrate.

1. Brief Summary

This disclosure is related to image/video coding technologies. Specifically, it is related to adding downsampling filter information for neural-network post-processing filters signalled in a video bitstream. The downsampling information herein can be information describing a neural network-based downsampling model and the corresponding parameters. The downsampling information herein can also be information describing a non-neural network-based downsampling model (e.g. bilinear filter or bicubic filter) and corresponding parameters. The ideas may be applied individually or in various combinations, for video bitstreams coded by any codec, e.g., the versatile video coding (VVC) standard and/or the versatile SEI messages for coded video bitstreams (VSEI) standard.

2. Abbreviations
APS Adaptation Parameter Set
AU Access Unit
CLVS Coded Layer Video Sequence
CLVSS Coded Layer Video Sequence Start
CRC Cyclic Redundancy Check
CVS Coded Video Sequence
FIR Finite Impulse Response
IRAP Intra Random Access Point
NAL Network Abstraction Layer
PPS Picture Parameter Set
PU Picture Unit
RASL Random Access Skipped Leading
SEI Supplemental Enhancement Information
STSA Step-wise Temporal Sublayer Access
VCL Video Coding Layer
VSEI versatile supplemental enhancement information (Rec. ITU-T H. 274|
ISO/IEC 23002-7)
VUI Video Usability Information
VVC versatile video coding (Rec. ITU-T H. 266 | ISO/IEC 23090-3)

3. Introduction

3.1. Video coding standards

Video coding standards have evolved primarily through the development of the well-known ITU-T and ISO/IEC standards. The ITU-T produced H. 261 and H. 263, ISO/IEC produced MPEG-1 and MPEG-4 Visual, and the two organizations jointly produced the H. 262/MPEG-2 Video and H. 264/MPEG-4 Advanced Video Coding (AVC) and H. 265/HEVC standards. Since H.262, the video coding standards are based on the hybrid video coding structure wherein temporal prediction plus transform coding are utilized. To explore the future video coding technologies beyond HEVC, the Joint Video Exploration Team (JVET) was founded by VCEG and MPEG jointly in 2015. Since then, many new methods have been adopted by JVET and put into the reference software named Joint Exploration Model (JEM) . The JVET was later renamed to be the Joint Video Experts Team (JVET) when the Versatile Video Coding (VVC) project officially started. VVC is the new coding standard, targeting at 50%bitrate reduction as compared to HEVC, that has been finalized by the JVET at its 19th meeting ended at July 1, 2020.

The Versatile Video Coding (VVC) standard (ITU-T H. 266 | ISO/IEC 23090-3) and the associated Versatile Supplemental Enhancement Information for coded video bitstreams (VSEI) standard (ITU-T H. 274 | ISO/IEC 23002-7) have been designed for use in a maximally broad range of applications, including both the traditional uses such as television broadcast, video conferencing, or playback from storage media, and also newer and more advanced use cases such as adaptive bit rate streaming, video region extraction, composition and merging of content from multiple coded video bitstreams, multiview video, scalable layered coding, and viewport-adaptive 360° immersive media.

The Essential Video Coding (EVC) standard (ISO/IEC 23094-1) is another video coding standard that has recently been developed by MPEG.

3.2. SEI messages in general and in VVC and VSEI

SEI messages assist in processes related to decoding, display or other purposes. However, SEI messages are not required for constructing the luma or chroma samples by the decoding process. Conforming decoders are not required to process this information for output order conformance. Some SEI messages are required for checking bitstream conformance and for output timing decoder conformance. Other SEI messages are not required for check bitstream conformance. Annex D of VVC specifies syntax and semantics for SEI message payloads for some SEI messages, and specifies the use of the SEI messages and VUI parameters for which the syntax and semantics are specified in ITU-T H. 274 | ISO/IEC 23002-7.

3.3. Signalling of neural-network post-filters

An existing design includes the specification of two SEI messages for signalling of neural-network post-filters, as follows.

4. Problems

The current design for the neural-network post-filter characteristics (NNPFC) SEI message has the following problems:

1) At the pre-processing stage, downsampling is a common processing step used in im-age/video coding. Reconstructed image/video with higher quality may be achieved if the post-processing filters are trained based on the specific downsampling filters. In one exam-ple, quality improvement of reconstructed image/video is desired before upsampling, while only the NNPFC SEI message specifying an NN upsampling filter is available. In this ex-ample, the neural network model for quality improvement can be finetuned or optimized based on the corresponding downsampling model first and then the model of quality im-provement is applied to the reconstructed content. This may achieve a higher quality for the reconstructed image/video than using a general model for quality improvement. Thus, it is helpful if the information of the downsampling filters is available for the post filters.

5. Detailed Solutions

To solve the above problems, methods as summarized below are disclosed. The solutions should be considered as examples to explain the general concepts and should not be interpreted in a narrow way. Furthermore, these solutions can be applied individually or combined in any manner. In the following description, the term picture may be replaced with any video unit, such as slice. The term “consecutive video units in output/decoding order” may be replaced with “aset of video units with same parameters (e.g., picture-level quantization parameters, picture types, temporal layer id) in output order” .

1) To solve problem 1, one or more of the following syntax elements may be signaled in a video message:

a. In one example, the video message may be a SEI or VUI message.

b. In one example, the downsampling_filter_type may be signalled to indicate the downsampling method used before encoding the associated video unit (such as picture/slice/block) .

c. In one example, the nnpfc_downsampling_id indicates the identifying number (index) for the NN-based downsampling filters.

d. In one example, if downsampling_filter_type is equal to a first value, such as 0, it indicates that neural network-based downsampling filter is used for downsam-pling the sequence.

i. In one example, the nnpfc_downsampling_mode_idc is defined to spec-ify how to interpret the way to determine neural network-based downsampling filter. For example,

1. nnpfc_downsampling_mode_idc equal to 0 specifies that the post-processing filter associated with the nnpfc_downsam-pling_id value is determined by external means.

2. nnpfc_downsampling_mode_idc equal to 1 specifies that the post-processing filter associated with the nnpfc_downsam-pling_id value is a neural network represented by the ISO/IEC 15938-17 bitstream contained in this SEI message.

3. nnpfc_downsampling_mode_idc equal to 2 specifies that the post-processing filter associated with the nnpfc_downsam-pling_id value is a neural network identified by a specified tag Uniform Resource Identifier (URI) (nnpfc_uri_tag [i] ) and neu-ral network information URI (nnpfc_uri [i] ) .

ii. In one example, following constrains shall be applied for the nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples syntax:

1. The specified nnpfc_pic_width_in_luma_samples shall be con-sistent with the width of the luma sample after applying the post-processing filter identified by nnpfc_id.

2. The specified nnpfc_pic_height_in_luma_samples shall be con-sistent with the height of the luma sample after applying the post-processing filter identified by nnpfc_id.

e. In one example, if downsampling_filter_type is equal to a second value, such as 1, it indicates that the downsampling filter is bilinear filter.

i. In one example, the nnpfc_downsampling_mode_idc is defined to spec-ify the downsampling filter.

2. nnpfc_downsampling_mode_idc equal to 3 specifies that the post-processing filter associated with the nnpfc_downsam-pling_id value is determined by a filter information nnpfc_downsampling_filter_info [i] .

f. In one example, the if downsampling_filter_type is equal to a third value, such as 2, it indicates that the downsampling filter is bicubic filter.

i. In one example, nnpfc_downsampling_mode_idc is defined to specify the downsampling filter.

1. nnpfc_downsampling_idc equal to 0 specifies that the post-pro-cessing filter associated with the nnpfc_downsampling_id value is determined by external means.

g. In one example, the if downsampling_filter_type is equal to a fourth value, such as 3, it indicates that the downsampling filter is RPR (reference picture resampling) filter.

2) In one example, the following syntax elements indicating complexity of neural network-based downsampling filter may be signaled in a video message:

a. In one example, the video message may be a SEI or VUI message.

b. In one example, the nnpfc_downsampling_idc is defined to specify the neural network-based downsampling filter.

c. In one example, nnpfc_downsampling_complexity_idc is definded.

i. In one example, the nnpfc_downsampling_complexity_idc equal to 0 specifies that no syntax element that indicates the complexity of the downsampling filter is present.

ii. In one example, the nnpfc_downsampling_complexity_idc equal to 1 specifies that syntax elements that indicates the complexity of downsam-pling filter is present.

d. In one example, when the nnpfc_downsampling_complexity_idc equal to 1, the following syntax elements are defined:

i. nnpfc_downsampling_parameter_type_idc indicates the type of param-eters.

1. In one example, nnpfc_parameter_type_idc equal to 0 indicates that the neural network uses only integer parameters.

2. In one example, nnpfc_parameter_type_idc equal to 1 indicates that the neural network uses only floating point.

3. In one example, nnpfc_parameter_type_idc equal to 2 indicates that the neural network uses only binary parameters.

ii. nnpfc_downsampling_log2_parameter_bit_length_minus3 indicates the bit length of the neural network parameters.

1. In one example, the nnpfc_downsampling_log2_parame-ter_bit_length_minus3 equal to 0, 1, 2, and 3 indicates that the neural network does not use parameters of bit length greater than 8, 16, 32, and 64, respectively.

iii. nnpfc_downsampling_num_parameters_idc indicates the maximum number of neural network parameters for the post processing filter.

iv. nnpfc_downsampling_num_kmac_operations_idc indicates the maxi-mum number of multiply-accumulate operations per sample of the downsampling filter.

3) The downsampling is performed at all the video unit (e.g., sequence/pic-ture/slice/tile/brick/subpicture/CTU/CTU row/one or multiple CUs or CTUs/CTBs) level.

a. In one example, the downsampling filter is performed for the frame level with size of its original resolution.

4) In one example, multiple downsampling filters may be applied for different video unit.

a. In one example, one downsampling filter is applied for all the color components and pictures. Thus, only one nnpfc_downsampling_id is signaled in the SEI mes-sage.

b. In one example, multiple downsampling filters are applied for different color components.

i. In one example, multiple nnpfc_downsampling_id are signaled in the or-der of Y, U, and V.

ii. In another example, nnpfc_downsampling_id_y, nnpfc_downsam-pling_id_u, and nnpfc_downsampling_id_v are signaled, respectively.

c. In one example, multiple downsampling filters are applied for different picture types.

i. In one example, multiple nnpfc_downsampling_id are signaled in the or-der of I slice, P slice, and B slice.

ii. In another example, nnpfc_downsampling_id_I, nnpfc_downsam-pling_id_P, and nnpfc_downsampling_id_B are signaled, respectively.

5) In one example, nnpfc_scaling_factor_width and nnpfc_scaling_factor_height which indi-cate the scaling factors of upsampling model identified by nnpfc_id is signaled.

a. In one example, nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples are used in the syntax:

i. In one example, the nnpfc_scaling_factor_width and nnpfc_scaling_fac-tor_height should be consistent with the nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples specified in the SEI message.

1. In one example, nnpfc_scaling_factor_width *width_input equal to nnpfc_pic_width_in_luma_samples where width_input de-notes the width of image/video before upsampling.

2. In one example, nnpfc_scaling_factor_height *height_input equal to nnpfc_pic_height_in_luma_samples where height_input denotes the height of image/video before upsampling.

ii. In one example, if the the nnpfc_scaling_factor_width and nnpfc_scal-ing_factor_height is not consistent with the nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples specified in the SEI message:

1. In one example, to achieve the same resolution with nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples, multiple upsamplings us-ing the upsampling model identified by nnpfc_id could be per-formed.

2. In one example, to achieve the same resolution with nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples, bilinear or bicubic filters could be applied after/before applying the upsampling model identified by nnpfc_id.

b. In one example, nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples are not used in the SEI message.

i. In one example, the width and height of luma sample array of the picture resulting by applying the post-processing filter identified by nnpfc_id, can de derived according to nnpfc_scaling_factor_width, nnpfc_scal-ing_factor_height, corresponging width of image/video before upsam-pling, and corresponging height of image/video before upsampling.

ii. In one example, the width and height of luma sample array of the picture resulting by applying the post-processing filter identified by nnpfc_id, are signaled, respectively.

1. In one example, the luma sample array of the picture resulting by applying the post-processing filter identified by nnpfc_id, are signaled, respectively.

2. In one example, nnpfc_scaled_pic_width_in_luma_samples is signaled, which specifies the width of the luma sample array of the picture resulting by applying the post-processing filter iden-tified by nnpfc_id to a cropped decoded output picture. The nnpfc_scaled_pic_width_in_luma_samples equal to nnpfc_scal-ing_factor_width *width_input where width_input denotes the width of image/video before upsampling.

3. In one example, nnpfc_scaled_pic_height_in_luma_samples is signaled, which specifies the height of the luma sample array of the picture resulting by applying the post-processing filter iden-tified by nnpfc_id to a cropped decoded output picture. Nnpfc_scaled_pic_height_in_luma_samples equal to nnpfc_scaling_factor_height *height_input where width_input denotes the width of image/video before upsampling.

6. Embodiments

Below are some example embodiments for the solution aspects summarized above in Section 5. Most relevant parts that have been added or modified are underlined, and some of the deleted parts are shown in. There may be some other changes that are editorial in nature and thus not highlighted.

6.1. Embodiment 1

This embodiment is for the solution items 1 to 4 and all their subitems, summarized above in Section 5.

6.1.1 Neural-network post-filter characteristics SEI message syntax

6.1.2 Neural-network post-filter characteristics SEI message semantics

This SEI message specifies a neural network that may be used as a post-processing filter. The use of specified post-processing filters for specific pictures is indicated with neural-network post-filter activation SEI messages.

nnpfc_purpose indicates the purpose of post-processing filter as specified in Table 2. The value of nnpfc_purpose shall be in the range of 0 to 2³² -2, inclusive. Values of nnpfc_purpose that do not appear in Table 2 are reserved for future specification by ITU-T | ISO/IEC and shall not be present in bitstreams conforming to this version of this Specification. Decoders conforming to this version of this Specification shall ignore SEI messages that contain reserved values of nnpfc_purpose.

Table 2 –Definition of nnpfc_purpose

NOTE 1 –When a reserved value of nnpfc_purpose is taken into use in the future by ITU-T |ISO/IEC, the syntax of this SEI message could be extended with syntax elements whose presence is conditioned by nnpfc_purpose being equal to that value.

When SubWidthC is equal to 1 and SubHeightC is equal to 1, nnpfc_purpose shall not be equal to 2 or 4.

nnpfc_out_sub_c_flag equal to 1 specifies that outSubWidthC is equal to 1 and outSubHeightC is equal to 1. nnpfc_out_sub_c_flag equal to 0 specifies that outSubWidthC is equal to 2 and outSubHeightC is equal to 1. When nnpfc_out_sub_c_flag is not present, outSubWidthC is inferred to be equal to SubWidthC and outSubHeightC is inferred to be equal to SubHeightC. If SubWidthC is equal to 2 and SubHeightC is equal to 1, nnpfc_out_sub_c_flag shall not be equal to 0.

nnpfc_scaling_factor_width specify the scaling factor of width by applying the post-processing filter identified by nnpfc_id.

nnpfc_scaling_factor_height specify the scaling factor of height by applying the post- processing filter identified by nnpfc_id.

nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples specify the width and height, respectively, of the luma sample array of the picture resulting by applying the post-processing filter identified by nnpfc_id to a cropped decoded output picture. When nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples are not present, they are inferred to be equal to CroppedWidth and CroppedHeight, respectively.

nnpfc_pic_width_in_luma_samples equal to nnpfc_scaling_factor_width *width_input where width_input denotes the width of image/video before upsampling.

nnpfc_pic_height_in_luma_samples equal to nnpfc_scaling_factor_height *height_input where width_input denotes the width of image/video before upsampling.

nnpfc_component_last_flag equal to 1 specifies that the last dimension in the input tensor inputTensor to the post-processing filter and the output tensor outputTensor resulting from the post-processing filter is used for the channel. nnpfc_component_last_flag equal to 0 specifies that the second dimension in the input tensor inputTensor to the post-processing filter and the output tensor outputTensor resulting from the post-processing filter is used for the channel..

NOTE 2 –The first dimension in the input tensor and in the output tensor is used for the batch index, which is a practice in some neural network frameworks. While the semantics of this SEI message use batch size equal to 1, it is up to the post-processing implementation to determine the batch size used as input to the neural network inference.

NOTE 3 –A colour component is an example of a channel.

nnpfc_downsampling_filter equal to 0 specifies that neural network-based downsampling filter is used for downsampling the sequence. nnpfc_downsampling_filter equal to 1 specifies that bilinear filter is used for downsampling the sequence. nnpfc_downsampling_filter equal to 2 specifies that bicubic filter is used for downsampling the sequence.

nnpfc_downsampling_id contains an identifying number that may be used to identify a post- processing filter. The value of nnpfc_id shall be in the range of 0 to 2³² -2, inclusive.

nnpfc_downsampling_mode_idc equal to 0 specifies that the post-processing filter associated with the nnpfc_id value is determined by external means not specified in this Specification.

nnpfc_mode_idc equal to 1 specifies that the post-processing filter associated with the nnpfc_id value is a neural network represented by the ISO/IEC 15938-17 bitstream contained in this SEI message.

nnpfc_mode_idc equal to 2 specifies that the post-processing filter associated with the nnpfc_id value is a neural network identified by a specified tag Uniform Resource Identifier (URI) (nnpfc_uri_tag [i] ) and neural network information URI (nnpfc_uri [i] ) .

nnpfc_mode_idc equal to 3 specifies that the post-processing filter associated with the nnpfc_id value is a bilinear or bicubic filter, which is identified by nnpfc_downsampling_filter_parameter_size and nnpfc_downsampling_filter_info [i] .

nnpfc_reserved_zero_bit shall be equal to 0.

nnpfc_uri_tag [i] contains a NULL-terminated UTF-8 character string specifying a tag URI. The UTF-8 character string contains a URI, with syntax and semantics as specified in IETF RFC 4151, uniquely identifying the format and associated information about the neural network used as the post-processing filter specified by nnrpf_uri [i] values.

NOTE 4 –nnrpf_uri_tag [i] elements represent a 'tag' URI, which allows uniquely identifying the format of neural network data specified by nnrpf_uri [i] values without needing a central registration authority.

nnpfc_uri [i] contains a NULL-terminated UTF-8 character string, as specified in IETF Internet Standard 63. The UTF-8 character string contains a URI, with syntax and semantics as specified in IETF Internet Standard 66, identifying the neural network information (e.g. data representation) used as the post-processing filter.

nnpfc_payload_byte [i] contains the i-th byte of a bitstream conforming to ISO/IEC 15938-17.The byte sequence nnpfc_payload_byte [i] for all present values of i shall be a complete bitstream that conforms to ISO/IEC 15938-17.

nnpfc_downsampling_filter_parameter_size specifies the bytes of each parameter of the post-processing filter.

nnpfc_downsampling_filter_info [i] contains the i-th byte of a bitstream which contains the parameters of downsampling filters.

nnpfc_downsampling_parameter_type_idc equal to 0 indicates that the neural network- based downsampling filter uses only integer parameters. nnpfc_parameter_type_flag equal to 1 indicates that the neural network may use only floating point. nnpfc_parameter_type_idc equal to 2 indicates that the neural network uses only binary parameters. nnpfc_parameter_type_idc equal to 3 is reserved for future specification.

nnpfc_downsampling_log2_parameter_bit_length_minus3 equal to 0, 1, 2, and 3 indicates that the neural network does not use parameters of bit length greater than 8, 16, 32, and 64, respectively. When nnpfc_parameter_type_idc is present and nnpfc_log2_parameter_bit_length_minus3 is not present the neural network does not use parameters of bit length greater than 1.

nnpfc_downsampling_num_parameters_idc indicates the maximum number of neural network parameters for the post processing filter in units of a power of 2048. nnpfc_num_parameters_idc equal to 0 indicates that the maximum number of neural network parameters is not specified. The value nnpfc_num_parameters_idc shall be in the range of 0 to 52, inclusive. Values of nnpfc_num_parameters_idc greater than 52 are reserved for future specification by ITU-T | ISO/IEC and shall not be present in bitstreams conforming to this version of this Specification. Decoders conforming to this version of this Specification shall ignore SEI messages that contain reserved values of nnpfc_num_parameters_idc.

If the value of nnpfc_num_parameters_idc is greater than zero, the variable maxNumParameters is derived as follows:

maxNumParameters = (2048 << nnpfc_num_parameters_idc) -1

It is a requirement of bitstream conformance that the number of neural network parameters of the post-processing filter shall be less than or equal to maxNumParameters.

nnpfc_downsampling_num_kmac_operations_idc greater than 0 specifies that the maximum number of multiply-accumulate operations per sample of the post-processing filter is less than or equal to nnpfc_num_kmac_operations_idc *1000. nnpfc_num_kmac_operations_idc equal to 0 specifies that the maximum number of multiply- accumulate operations of the network is not specified. The value of nnpfc_num_kmac_operations_idc shall be in the range of 0 to 2³² -1, inclusive.

More details of the embodiments of the present disclosure will be described below which are related to neural-network post-filter with downsampling information. The embodiments of the present disclosure should be considered as examples to explain the general concepts and should not be interpreted in a narrow way. Furthermore, these embodiments can be applied individually or combined in any manner.

As used herein, the term “video unit” may represent a color component, a sub-picture, a picture, a slice, a tile, a coding tree unit (CTU) , a CTU row, groups of CTU, a coding unit (CU) , a prediction unit (PU) , a transform unit (TU) , a coding tree block (CTB) , a coding block (CB) , a prediction block (PB) , a transform block (TB) , a sub-block of a video block, a sub-region within a video block, a video processing unit comprising multiple samples/pixels, and/or the like. A video unit may be rectangular or non-rectangular. Moreover, the term “post-processing filter” and “post-filter” may be used interchangeably.

Fig. 5 illustrates a flowchart of a method 500 for video processing in accordance with some embodiments of the present disclosure. As shown in Fig. 5, at 502, a conversion between a current video unit of a video and a bitstream of the video is performed. In some embodiments, the conversion may include encoding the current video unit into the bitstream. Alternatively or additionally, the conversion may include decoding the current video unit from the bitstream.

In some embodiments, the bitstream comprises information of a downsampling filter for obtaining the current video unit. That is, at a pre-processing stage, a downsampling process with the downsampling filter may be applied to a video unit of the original video, to obtain the current video unit to be encoded into the bitstream. In one example, the information of the downsampling filter may be comprised in a supplemental enhancement information (SEI) message. Alternatively, the information of the downsampling filter may be comprised in a video usability information (VUI) message in the bitstream. In aid of such information of the downsampling filter, a post-processing filter for quality improvement can be finetuned or optimized based on the corresponding downsampling filter information at first. Then, the post-processing filter may be applied to the reconstructed video for the purpose of quality improvement.

In view of the above, the information of the downsampling filter for obtaining the current video unit is signaled in the bitstream. Compared with the conventional solution, where such information is not signaled, the proposed method can advantageously enable an optimization of a post-processing filter for quality improvement based on the information of the downsampling filter, and thus the quality of the video after post-processing can be improved.

In some embodiments, the information may comprise a first indication indicating a type of the downsampling filter. By way of example rather than limitation, the first indication may be a syntax element downsampling_filter_type. Additionally, the information may comprise a second indication indicating an identifying number or an index of the downsampling filter. By way of example rather than limitation, the second indication may be a syntax element nnpfc_downsampling_id.

In some embodiments, the first indication equal to a first value (e.g., 0 or the like) may indicate that the downsampling filter is a neural network-based downsampling filter. The first indication equal to a second value (e.g., 1 or the like) may indicate that the downsampling filter is a bilinear filter. The first indication equal to a third value (e.g., 2 or the like) may indicate that the downsampling filter is a bicubic filter, or the first indication equal to a fourth value (e.g., 3 or the like) may indicate that the downsampling filter is a reference picture resampling (RPR) filter. It should be understood that the above illustrations are described merely for purpose of description. The scope of the present disclosure is not limited in this respect.

In some embodiments, the information may comprise a third indication indicates how to determine the downsampling filter. By way of example rather than limitation, the third indication may be a syntax element nnpfc_downsampling_mode_idc.

In some embodiments, the third indication equal to a fifth value (e.g., 0 or the like) may indicate that the downsampling filter is determined based on a pre-defined scheme. The third indication equal to a sixth value (e.g., 1 or the like) may indicate that the downsampling filter comprises a neural network obtained from the bitstream. For example, the neural network may be represented by the ISO/IEC 15938-17 bitstream contained in this SEI message. The third indication equal to a seventh value (e.g., 2 or the like) may indicate that the downsampling filter comprises a neural network obtained based on one or more indications in the bitstream. For example, the one or more indications may comprise at least one of a specified tag Uniform Resource Identifier (URI) (such as, nnpfc_uri_tag [i] ) or a neural network information URI (such as, nnpfc_uri [i] ) . The third indication equal to an eighth value (e.g., 3 or the like) may indicate that a set of parameters of the downsampling filter is obtained from the bitstream. For example, the set of parameters may be indicated by a fourth indication in the bitstream. The fourth indication may be a syntax element nnpfc_downsampling_filter_info. It should be understood that the above illustrations are described merely for purpose of description. The scope of the present disclosure is not limited in this respect.

In some embodiments, if the first indication may be equal to the first value, the third indication may be allowed to be equal to one of the fifth value, the sixth value, or the seventh value. Additionally or alternatively, if the first indication may be equal to one of the second value, the third value or the fourth value, the third indication may be allowed to be equal to one of the fifth value, or the eighth value.

In some embodiments, a value of a first syntax element shall be consistent with a width of luma sample after applying a post-processing filter identified by a second syntax element. The first syntax element indicates a width of a luma sample array of a video unit resulting by applying the post-processing filter identified by the second syntax element to a decoded current video unit. The second syntax element indicates an identifying number used to identify the post-processing filter, and a value of a third syntax element may be consistent with a height of luma sample after applying the post-processing filter identified by the second syntax element. Moreover, the third syntax element indicates a height of a luma sample array of the video unit resulting by applying the post-processing filter identified by the second syntax element to the decoded current video unit. By way of example rather than limitation, the first syntax element may be a syntax element nnpfc_pic_width_in_luma_samples, the second syntax element may be a syntax element nnpfc_id, and the third syntax element may be a syntax element nnpfc_pic_height_in_luma_samples.

In some embodiments, the downsampling filter may be a neural network-based downsampling filter. In such a case, the bitstream may comprise a fifth indication indicating whether at least one indication indicating complexity of the neural network-based downsampling filter is present in the bitstream. By way of example rather than limitation, the fifth indication may be a syntax element nnpfc_downsampling_complexity_idc. For example, the fifth indication equal to a ninth value (e.g., 0 or the like) indicates that the at least one indication is not present in the bitstream. The fifth indication equal to a tenth value (e.g., 1 or the like) indicates that the at least one indication is present in the bitstream. It should be understood that the above illustrations are described merely for purpose of description. The scope of the present disclosure is not limited in this respect.

In some embodiments, the information may comprise a sixth indication specifying the neural network-based downsampling filter. By way of example rather than limitation, the sixth indication may be a syntax element nnpfc_downsampling_idc.

In some additional embodiments, the at least one indication may comprise a seventh indication indicating a type of parameters of the neural network-based downsampling filter. By way of example rather than limitation, the seventh indication may be a syntax element nnpfc_downsampling_parameter_type_idc. For example, the seventh indication equal to an eleventh value (e.g., 0 or the like) indicates the type of the parameters is integer. The seventh indication equal to a twelfth value (e.g., 1 or the like) indicates the type of the parameters is floating point, or the seventh indication equal to a thirteenth value (e.g., 2 or the like) indicates the type of the parameters is binary. It should be understood that the above illustrations are described merely for purpose of description. The scope of the present disclosure is not limited in this respect.

In some embodiments, the at least one indication may comprise an eighth indication indicating a bit length of parameters of the neural network-based downsampling filter. By way of example rather than limitation, the eighth indication may be a syntax element nnpfc_downsampling_log2_parameter_bit_length_minus3. For example, the eighth indication equal to a fourteenth value (e.g., 0 or the like) indicates that the bit length of the parameters is smaller than or equal to 8. The eighth indication equal to a fifteenth value (e.g., 1 or the like) indicates that the bit length of the parameters may be smaller than or equal to 16. The eighth indication equal to a sixteenth value (e.g., 2 or the like) indicates that the bit length of the parameters is smaller than or equal to 32. The eighth indication equal to a seventeenth value (e.g., 3 or the like) indicates that the bit length of the parameters is smaller than or equal to 64. It should be understood that the above illustrations are described merely for purpose of description. The scope of the present disclosure is not limited in this respect.

In some additional or alternative embodiments, the at least one indication may comprise a ninth indication indicating the maximum number of parameters of the neural network-based downsampling filter. By way of example rather than limitation, the ninth indication may be a syntax element nnpfc_downsampling_num_parameters_idc. Additionally or alternatively, the at least one indication may comprise a tenth indication indicating the maximum number of multiply-accumulate operations per sample of the neural network-based downsampling filter. For example, the tenth indication may be a syntax element nnpfc_downsampling_num_kmac_operations_idc.

In some embodiments, a downsampling process may be performed at one of the following levels: a sequence level, a frame level, a picture level, a slice level, a tile level, a brick level, a subpicture level, a coding transform unit (CTU) level, a CTU row level, a level of one or more coding units (CUs) , a level of one or more CTUs, or a level of one or more coding transform blocks (CTBs) . For example, the downsampling process may be performed for all video units at a specific level. Alternatively, the downsampling process may be only performed for a part of video units at the specific level. By way of example, the downsampling process may be performed at the frame level with a size of an original resolution for a frame of the video.

In some embodiments, the downsampling filter may be comprised in a plurality of downsampling filters, and the plurality of downsampling filters may be applied for different video units of the video.

In some embodiments, the downsampling filter may be applied for all color components and pictures of the video, and only one second indication (e.g., only one syntax element nnpfc_downsampling_id) may be indicated in the bitstream. In some alternative embodiments, the downsampling filter may be comprised in a plurality of downsampling filters, and the plurality of downsampling filters may be applied for different color components of the video. For example, the different color components may comprise a first color component, a second color component and a third color component. By way of example, the first color component may be color component Y, the second color component may be color component U, and the third color component may be color component V. It should be understood that the above examples are described merely for purpose of description. The scope of the present disclosure is not limited in this respect.

In some embodiments, a plurality of eleventh indications may be signaled in an order of the first color component, the second color component and the third color component. An eleventh indication indicates an identifying number or an index of one of the plurality of downsampling filters. By way of example rather than limitation, the eleventh indication may be a syntax element nnpfc_downsampling_id.

Alternatively, a twelfth indication, a thirteenth indication and a fourteenth indication may be indicated in the bitstream. The twelfth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the first color component. The thirteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the second color component, and the fourteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the third color component. By way of example rather than limitation, the twelfth indication may be a syntax element nnpfc_downsampling_id_y, the thirteenth indication may be a syntax element nnpfc_downsampling_id_u, and the fourteenth indication may be a syntax element nnpfc_downsampling_id_v. It should be understood that the above illustrations are described merely for purpose of description. The scope of the present disclosure is not limited in this respect.

In some embodiments, the plurality of downsampling filters may be applied for different picture types of the video. For example, the different picture types may comprise a first picture type, a second picture type and a third picture type. By way of example, the first picture type may be I slice, the second picture type may be P slice, and the third picture type may be B slice. It should be understood that the above examples are described merely for purpose of description. The scope of the present disclosure is not limited in this respect.

In some embodiments, a plurality of fifteenth indications may be signaled in an order of the first picture type, the second picture type and the third picture type. A fifteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters. By way of example rather than limitation, the fifteenth indication may be a syntax element nnpfc_downsampling_id.

Alternatively, a sixteenth indication, a seventeenth indication and an eighteenth indication may be indicated in the bitstream. The sixteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the first picture type. The seventeenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the second picture type. The eighteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the third picture type. For example, the sixteenth indication may be a syntax element nnpfc_downsampling_id_I, the seventeenth indication may be a syntax element nnpfc_downsampling_id_P, and the eighteenth indication may be a syntax element nnpfc_downsampling_id_B. It should be understood that the above examples are described merely for purpose of description. The scope of the present disclosure is not limited in this respect.

In some embodiments, the bitstream may further comprise a nineteenth indication and a twentieth indication. The nineteenth indication indicates a width scaling factor of a post-processing filter for processing a reconstruction of the current video unit, and the twentieth indication indicates a length scaling factor of the post-processing filter. In one example, the post-processing filter may be identified by a syntax element nnpfc_id. By way of example rather than limitation, the nineteenth indication may be a syntax element nnpfc_scaling_factor_width, and the twentieth indication may be a syntax element nnpfc_scaling_factor_height.

In some embodiments, the bitstream may further comprise a twenty-first indication and a twenty-second indication. The twenty-first indication indicates a width of a luma sample array of a video unit resulting by applying the post-processing filter to a decoded current video unit, and the twenty-second indication indicates a height of the luma sample array of the video unit resulting by applying the post-processing filter to the decoded current video unit. By way of example rather than limitation, the twenty-first indication may be a syntax element nnpfc_pic_width_in_luma_samples, and the twenty-second indication may be a syntax element nnpfc_pic_height_in_luma_samples.

In some embodiments, a value of the nineteenth indication may be consistent with a value of the twenty-first indication. For example, a product of the value of the nineteenth indication and a width of the current video unit may be equal to the value of the twenty-first indication. Additionally or alternatively, a value of the twentieth indication may be consistent with a value of the twenty-second indication. For example, a product of the value of the twentieth indication and a height of the current video unit may be equal to the value of the twenty-second indication.

In some embodiments, if a value of the nineteenth indication is not consistent with a value of the twenty-first indication and/or a value of the twentieth indication is not consistent with a value of the twenty-second indication, a plurality of upsampling processes may be performed on the reconstruction of the current video unit by using the post-processing filter, so as to achieve the same resolution specified with the twenty-first indication and twenty-second indication. Alternatively, a bilinear filter or a bicubic filter may be applied to the reconstruction of the current video unit in combination with the post-processing filter, so as to achieve the same resolution specified with the twenty-first indication and twenty-second indication.

In some embodiments, the twenty-first indication and the twenty-second indication may be absent from the bitstream. In such a case, the width of the luma sample array may be determined based on a value of the nineteenth indication and a width of the current video unit. Moreover, the height of the luma sample array may be determined based on a value of the twentieth indication and a height of the current video unit. Additionally or alternatively, the luma sample array may be indicted in the bitstream.

In some embodiments, the width of the luma sample array and the height of the luma sample array may be indicated in the bitstream. In one example, the width of the luma sample array may be indicated by a twenty-third indication. By way of example rather than limitation, the twenty-third indication may be a syntax element nnpfc_scaled_pic_width_in_luma_samples. A value of the twenty-third indication may be equal to a product of the value of the nineteenth indication and a width of the current video unit. In an additional or alternative example, the height of the luma sample array may be indicated by a twenty-fourth indication. By way of example rather than limitation, the twenty-fourth indication may be a syntax element nnpfc_scaled_pic_height_in_luma_samples. a value of the twenty-fourth indication may be equal to a product of the value of the twentieth indication and a height of the current video unit.

It should be understood that the any of the above-mentioned indication may also be a syntax element represented by any other suitable string different from the aforementioned name. The scope of the present disclosure is not limited in this respect.

According to further embodiments of the present disclosure, a non-transitory computer-readable recording medium is provided. The non-transitory computer-readable recording medium stores a bitstream of a video which is generated by a method performed by an apparatus for video processing. In the method, a conversion between a current video unit of the video and the bitstream is performed. The bitstream comprises information of a downsampling filter for obtaining the current video unit.

According to still further embodiments of the present disclosure, a method for storing bitstream of a video is provided. According to the method, a conversion between a current video unit of the video and the bitstream is performed. The bitstream comprises information of a downsampling filter for obtaining the current video unit. Moreover, the bitstream is stored in a non-transitory computer-readable recording medium.

Implementations of the present disclosure can be described in view of the following clauses, the features of which can be combined in any reasonable manner.

Clause 1. A method for video processing, comprising: performing a conversion between a current video unit of a video and a bitstream of the video, wherein the bitstream comprises information of a downsampling filter for obtaining the current video unit.

Clause 2. The method of clause 1, wherein the information is comprised in a supplemental enhancement information (SEI) message or a video usability information (VUI) message in the bitstream.

Clause 3. The method of clause 1, wherein the information comprises a first indication indicating a type of the downsampling filter.

Clause 4. The method of clause 3, wherein the first indication comprises a syntax element downsampling_filter_type.

Clause 5. The method of any of clauses 1-4, wherein the information comprises a second indication indicating an identifying number or an index of the downsampling filter.

Clause 6. The method of clause 5, wherein the second indication comprises a syntax element nnpfc_downsampling_id.

Clause 7. The method of any of clauses 3-6, wherein the first indication equal to a first value indicates that the downsampling filter is a neural network-based downsampling filter, or the first indication equal to a second value indicates that the downsampling filter is a bilinear filter, or the first indication equal to a third value indicates that the downsampling filter is a bicubic filter, or the first indication equal to a fourth value indicates that the downsampling filter is a reference picture resampling (RPR) filter.

Clause 8. The method of clause 7, wherein the information comprises a third indication indicates how to determine the downsampling filter.

Clause 9. The method of clause 8, wherein the third indication comprises a syntax element nnpfc_downsampling_mode_idc.

Clause 10. The method of any of clauses 8-9, wherein the third indication equal to a fifth value indicates that the downsampling filter is determined based on a pre-defined scheme, or the third indication equal to a sixth value indicates that the downsampling filter comprises a neural network obtained from the bitstream, or the third indication equal to a seventh value indicates that the downsampling filter comprises a neural network obtained based on one or more indications in the bitstream, or the third indication equal to an eighth value indicates that a set of parameters of the downsampling filter is obtained from the bitstream.

Clause 11. The method of clause 10, wherein the one or more indications comprise at least one of a specified tag Uniform Resource Identifier (URI) or a neural network information URI.

Clause 12. The method of any of clauses 10-11, wherein the set of parameters is indicated by a fourth indication in the bitstream.

Clause 13. The method of clause 12, wherein the fourth indication comprises a syntax element nnpfc_downsampling_filter_info.

Clause 14. The method of any of clauses 10-13, wherein if the first indication is equal to the first value, the third indication is allowed to be equal to one of the fifth value, the sixth value, or the seventh value, or if the first indication is equal to one of the second value, the third value or the fourth value, the third indication is allowed to be equal to one of the fifth value, or the eighth value.

Clause 15. The method of any of clauses 1-14, wherein a value of a first syntax element is consistent with a width of luma sample after applying a post-processing filter identified by a second syntax element, the first syntax element indicates a width of a luma sample array of a video unit resulting by applying the post-processing filter identified by the second syntax element to a decoded current video unit, and the second syntax element indicates an identifying number used to identify the post-processing filter, and a value of a third syntax element is consistent with a height of luma sample after applying the post-processing filter identified by the second syntax element, the third syntax element indicates a height of a luma sample array of the video unit resulting by applying the post-processing filter identified by the second syntax element to the decoded current video unit.

Clause 16. The method of clause 15, wherein the first syntax element comprises a syntax element nnpfc_pic_width_in_luma_samples, the second syntax element comprises a syntax element nnpfc_id, and the third syntax element comprises a syntax element nnpfc_pic_height_in_luma_samples.

Clause 17. The method of any of clauses 1-16, wherein the downsampling filter is a neural network-based downsampling filter, and the bitstream comprises a fifth indication indicating whether at least one indication indicating complexity of the neural network-based downsampling filter is present in the bitstream.

Clause 18. The method of clause 17, wherein the fifth indication comprises a syntax element nnpfc_downsampling_complexity_idc.

Clause 19. The method of any of clauses 17-18, wherein the fifth indication equal to a ninth value indicates that the at least one indication is not present in the bitstream, or the fifth indication equal to a tenth value indicates that the at least one indication is present in the bitstream.

Clause 20. The method of any of clauses 1-19, wherein the information comprises a sixth indication specifying the neural network-based downsampling filter.

Clause 21. The method of clause 20, wherein the sixth indication comprises a syntax element nnpfc_downsampling_idc.

Clause 22. The method of any of clauses 17-21, wherein the at least one indication comprises a seventh indication indicating a type of parameters of the neural network-based downsampling filter.

Clause 23. The method of clause 22, wherein the seventh indication comprises a syntax element nnpfc_downsampling_parameter_type_idc.

Clause 24. The method of any of clauses 22-23, wherein the seventh indication equal to an eleventh value indicates the type of the parameters is integer, or the seventh indication equal to a twelfth value indicates the type of the parameters is floating point, or the seventh indication equal to a thirteenth value indicates the type of the parameters is binary.

Clause 25. The method of any of clauses 17-25, wherein the at least one indication comprises an eighth indication indicating a bit length of parameters of the neural network-based downsampling filter.

Clause 26. The method of clause 25, wherein the eighth indication comprises a syntax element nnpfc_downsampling_log2_parameter_bit_length_minus3.

Clause 27. The method of any of clauses 25-26, wherein the eighth indication equal to a fourteenth value indicates that the bit length of the parameters is smaller than or equal to 8, or the eighth indication equal to a fifteenth value indicates that the bit length of the parameters is smaller than or equal to 16, or the eighth indication equal to a sixteenth value indicates that the bit length of the parameters is smaller than or equal to 32, or the eighth indication equal to a seventeenth value indicates that the bit length of the parameters is smaller than or equal to 64.

Clause 28. The method of any of clauses 17-27, wherein the at least one indication comprises a ninth indication indicating the maximum number of parameters of the neural network-based downsampling filter.

Clause 29. The method of clause 28, wherein the ninth indication comprises a syntax element nnpfc_downsampling_num_parameters_idc.

Clause 30. The method of any of clauses 17-29, wherein the at least one indication comprises a tenth indication indicating the maximum number of multiply-accumulate operations per sample of the neural network-based downsampling filter.

Clause 31. The method of clause 30, wherein the tenth indication comprises a syntax element nnpfc_downsampling_num_kmac_operations_idc.

Clause 32. The method of any of clauses 1-31, wherein a downsampling process is performed at one of the following levels: a sequence level, a frame level, a picture level, a slice level, a tile level, a brick level, a subpicture level, a coding transform unit (CTU) level, a CTU row level, a level of one or more coding units (CUs) , a level of one or more CTUs, or a level of one or more coding transform blocks (CTBs) .

Clause 33. The method of clause 32, wherein the downsampling process is performed at the frame level with a size of an original resolution for a frame of the video.

Clause 34. The method of any of clauses 5-33, wherein the downsampling filter is applied for all color components and pictures of the video, and only one second indication is indicated in the bitstream.

Clause 35. The method of any of clauses 1-33, wherein the downsampling filter is comprised in a plurality of downsampling filters, and the plurality of downsampling filters are applied for different video units of the video.

Clause 36. The method of any of clauses 1-33, wherein the downsampling filter is comprised in a plurality of downsampling filters, and the plurality of downsampling filters are applied for different color components of the video.

Clause 37. The method of clause 36, wherein the different color components comprise a first color component, a second color component and a third color component, a plurality of eleventh indications are signaled in an order of the first color component, the second color component and the third color component, and an eleventh indication indicates an identifying number or an index of one of the plurality of downsampling filters.

Clause 38. The method of clause 37, wherein the eleventh indication comprises a syntax element nnpfc_downsampling_id.

Clause 39. The method of clause 36, wherein the different color components comprise a first color component, a second color component and a third color component, a twelfth indication, a thirteenth indication and a fourteenth indication are indicated in the bitstream, the twelfth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the first color component, the thirteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the second color component, and the fourteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the third color component.

Clause 40. The method of clause 39, wherein the twelfth indication comprises a syntax element nnpfc_downsampling_id_y, the thirteenth indication comprises a syntax element nnpfc_downsampling_id_u, and the fourteenth indication comprises a syntax element nnpfc_downsampling_id_v.

Clause 41. The method of any of clauses 37-40, wherein the first color component is color component Y, the second color component is color component U, and the third color component is color component V.

Clause 42. The method of any of clauses 1-41, wherein the downsampling filter is comprised in a plurality of downsampling filters, and the plurality of downsampling filters are applied for different picture types of the video.

Clause 43. The method of clause 42, wherein the different picture types comprise a first picture type, a second picture type and a third picture type, a plurality of fifteenth indications are signaled in an order of the first picture type, the second picture type and the third picture type, and a fifteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters.

Clause 44. The method of clause 43, wherein the fifteenth indication comprises a syntax element nnpfc_downsampling_id.

Clause 45. The method of clause 42, wherein the different picture types comprise a first picture type, a second picture type and a third picture type, a sixteenth indication, a seventeenth indication and an eighteenth indication are indicated in the bitstream, the sixteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the first picture type, the seventeenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the second picture type, and the eighteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the third picture type.

Clause 46. The method of clause 45, wherein the sixteenth indication comprises a syntax element nnpfc_downsampling_id_I, the seventeenth indication comprises a syntax element nnpfc_downsampling_id_P, and the eighteenth indication comprises a syntax element nnpfc_downsampling_id_B.

Clause 47. The method of any of clauses 43-46, wherein the first picture type is I slice, the second picture type is P slice, and the third picture type is B slice.

Clause 48. The method of any of clauses 1-47, wherein the bitstream further comprises a nineteenth indication and a twentieth indication, the nineteenth indication indicates a width scaling factor of a post-processing filter for processing a reconstruction of the current video unit, and the twentieth indication indicates a length scaling factor of the post-processing filter.

Clause 49. The method of clause 48, wherein the nineteenth indication comprises a syntax element nnpfc_scaling_factor_width, and the twentieth indication comprises a syntax element nnpfc_scaling_factor_height.

Clause 50. The method of any of clauses 48-49, wherein the post-processing filter is identified by a syntax element nnpfc_id.

Clause 51. The method of any of clauses 48-50, wherein the bitstream further comprises a twenty-first indication and a twenty-second indication, the twenty-first indication indicates a width of a luma sample array of a video unit resulting by applying the post-processing filter to a decoded current video unit, and the twenty-second indication indicates a height of the luma sample array of the video unit resulting by applying the post-processing filter to the decoded current video unit.

Clause 52. The method of clause 51, wherein the twenty-first indication comprises a syntax element nnpfc_pic_width_in_luma_samples, and the twenty-second indication comprises a syntax element nnpfc_pic_height_in_luma_samples.

Clause 53. The method of any of clauses 51-52, wherein a value of the nineteenth indication is consistent with a value of the twenty-first indication, and a value of the twentieth indication is consistent with a value of the twenty-second indication.

Clause 54. The method of clause 53, wherein a product of the value of the nineteenth indication and a width of the current video unit is equal to the value of the twenty-first indication.

Clause 55. The method of any of clauses 53-54, wherein a product of the value of the twentieth indication and a height of the current video unit is equal to the value of the twenty-second indication.

Clause 56. The method of any of clauses 51-52, wherein if a value of the nineteenth indication is not consistent with a value of the twenty-first indication and a value of the twentieth indication is not consistent with a value of the twenty-second indication, a plurality of upsampling processes are performed on the reconstruction of the current video unit by using the post-processing filter.

Clause 57. The method of any of clauses 51-52, wherein if a value of the nineteenth indication is not consistent with a value of the twenty-first indication and a value of the twentieth indication is not consistent with a value of the twenty-second indication, a bilinear filter or a bicubic filter is applied to the reconstruction of the current video unit in combination with the post-processing filter.

Clause 58. The method of any of clauses 48-50, wherein a twenty-first indication and a twenty-second indication are absent from the bitstream, the twenty-first indication indicates a width of a luma sample array of a video unit resulting by applying the post-processing filter to a decoded current video unit, and the twenty-second indication indicates a height of the luma sample array of the video unit resulting by applying the post-processing filter to the decoded current video unit.

Clause 59. The method of clause 58, wherein the twenty-first indication comprises a syntax element nnpfc_pic_width_in_luma_samples, and the twenty-second indication comprises a syntax element nnpfc_pic_height_in_luma_samples.

Clause 60. The method of any of clauses 58-59, wherein the width of the luma sample array is determined based on a value of the nineteenth indication and a width of the current video unit, and the height of the luma sample array is determined based on a value of the twentieth indication and a height of the current video unit.

Clause 61. The method of any of clauses 58-60, wherein the luma sample array is indicted in the bitstream.

Clause 62. The method of any of clauses 58-61, wherein the width of the luma sample array and the height of the luma sample array are indicated in the bitstream.

Clause 63. The method of clause 62, wherein the width of the luma sample array is indicated by a twenty-third indication.

Clause 64. The method of clause 63, wherein the twenty-third indication comprises a syntax element nnpfc_scaled_pic_width_in_luma_samples.

Clause 65. The method of any of clauses 63-64, wherein a value of the twenty-third indication is equal to a product of the value of the nineteenth indication and a width of the current video unit.

Clause 66. The method of any of clauses 62-65, wherein the height of the luma sample array is indicated by a twenty-fourth indication.

Clause 67. The method of clause 66, wherein the twenty-fourth indication comprises a syntax element nnpfc_scaled_pic_height_in_luma_samples.

Clause 68. The method of any of clauses 66-67, wherein a value of the twenty-fourth indication is equal to a product of the value of the twentieth indication and a height of the current video unit.

Clause 69. The method of any of clauses 1-68, wherein the conversion includes encoding the current video unit into the bitstream.

Clause 70. The method of any of clauses 1-68, wherein the conversion includes decoding the current video unit from the bitstream.

Clause 71. An apparatus for video processing comprising a processor and a non-transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform a method in accordance with any of clauses 1-70.

Clause 72. A non-transitory computer-readable storage medium storing instructions that cause a processor to perform a method in accordance with any of clauses 1-70.

Clause 73. A non-transitory computer-readable recording medium storing a bitstream of a video which is generated by a method performed by an apparatus for video processing, wherein the method comprises: performing a conversion between a current video unit of the video and the bitstream, wherein the bitstream comprises information of a downsampling filter for obtaining the current video unit.

Clause 74. A method for storing a bitstream of a video, comprising: performing a conversion between a current video unit of the video and the bitstream, wherein the bitstream comprises information of a downsampling filter for obtaining the current video unit; and storing the bitstream in a non-transitory computer-readable recording medium.

Example Device

Fig. 6 illustrates a block diagram of a computing device 600 in which various embodiments of the present disclosure can be implemented. The computing device 600 may be implemented as or included in the source device 110 (or the video encoder 114 or 200) or the destination device 120 (or the video decoder 124 or 300) .

It would be appreciated that the computing device 600 shown in Fig. 6 is merely for purpose of illustration, without suggesting any limitation to the functions and scopes of the embodiments of the present disclosure in any manner.

As shown in Fig. 6, the computing device 600 includes a general-purpose computing device 600. The computing device 600 may at least comprise one or more processors or processing units 610, a memory 620, a storage unit 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660.

In some embodiments, the computing device 600 may be implemented as any user terminal or server terminal having the computing capability. The server terminal may be a server, a large-scale computing device or the like that is provided by a service provider. The user terminal may for example be any type of mobile terminal, fixed terminal, or portable terminal, including a mobile phone, station, unit, device, multimedia computer, multimedia tablet, Internet node, communicator, desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, personal communication system (PCS) device, personal navigation device, personal digital assistant (PDA) , audio/video player, digital camera/video camera, positioning device, television receiver, radio broadcast receiver, E-book device, gaming device, or any combination thereof, including the accessories and peripherals of these devices, or any combination thereof. It would be contemplated that the computing device 600 can support any type of interface to a user (such as “wearable” circuitry and the like) .

The processing unit 610 may be a physical or virtual processor and can implement various processes based on programs stored in the memory 620. In a multi-processor system, multiple processing units execute computer executable instructions in parallel so as to improve the parallel processing capability of the computing device 600. The processing unit 610 may also be referred to as a central processing unit (CPU) , a microprocessor, a controller or a microcontroller.

The computing device 600 typically includes various computer storage medium. Such medium can be any medium accessible by the computing device 600, including, but not limited to, volatile and non-volatile medium, or detachable and non-detachable medium. The memory 620 can be a volatile memory (for example, a register, cache, Random Access Memory (RAM) ) , a non-volatile memory (such as a Read-Only Memory (ROM) , Electrically Erasable Programmable Read-Only Memory (EEPROM) , or a flash memory) , or any combination thereof. The storage unit 630 may be any detachable or non-detachable medium and may include a machine-readable medium such as a memory, flash memory drive, magnetic disk or another other media, which can be used for storing information and/or data and can be accessed in the computing device 600.

The computing device 600 may further include additional detachable/non-detachable, volatile/non-volatile memory medium. Although not shown in Fig. 6, it is possible to provide a magnetic disk drive for reading from and/or writing into a detachable and non-volatile magnetic disk and an optical disk drive for reading from and/or writing into a detachable non-volatile optical disk. In such cases, each drive may be connected to a bus (not shown) via one or more data medium interfaces.

The communication unit 640 communicates with a further computing device via the communication medium. In addition, the functions of the components in the computing device 600 can be implemented by a single computing cluster or multiple computing machines that can communicate via communication connections. Therefore, the computing device 600 can operate in a networked environment using a logical connection with one or more other servers, networked personal computers (PCs) or further general network nodes.

The input device 650 may be one or more of a variety of input devices, such as a mouse, keyboard, tracking ball, voice-input device, and the like. The output device 660 may be one or more of a variety of output devices, such as a display, loudspeaker, printer, and the like. By means of the communication unit 640, the computing device 600 can further communicate with one or more external devices (not shown) such as the storage devices and display device, with one or more devices enabling the user to interact with the computing device 600, or any devices (such as a network card, a modem and the like) enabling the computing device 600 to communicate with one or more other computing devices, if required. Such communication can be performed via input/output (I/O) interfaces (not shown) .

In some embodiments, instead of being integrated in a single device, some or all components of the computing device 600 may also be arranged in cloud computing architecture. In the cloud computing architecture, the components may be provided remotely and work together to implement the functionalities described in the present disclosure. In some embodiments, cloud computing provides computing, software, data access and storage service, which will not require end users to be aware of the physical locations or configurations of the systems or hardware providing these services. In various embodiments, the cloud computing provides the services via a wide area network (such as Internet) using suitable protocols. For example, a cloud computing provider provides applications over the wide area network, which can be accessed through a web browser or any other computing components. The software or components of the cloud computing architecture and corresponding data may be stored on a server at a remote position. The computing resources in the cloud computing environment may be merged or distributed at locations in a remote data center. Cloud computing infrastructures may provide the services through a shared data center, though they behave as a single access point for the users. Therefore, the cloud computing architectures may be used to provide the components and functionalities described herein from a service provider at a remote location. Alternatively, they may be provided from a conventional server or installed directly or otherwise on a client device.

The computing device 600 may be used to implement video encoding/decoding in embodiments of the present disclosure. The memory 620 may include one or more video coding modules 625 having one or more program instructions. These modules are accessible and executable by the processing unit 610 to perform the functionalities of the various embodiments described herein.

In the example embodiments of performing video encoding, the input device 650 may receive video data as an input 670 to be encoded. The video data may be processed, for example, by the video coding module 625, to generate an encoded bitstream. The encoded bitstream may be provided via the output device 660 as an output 680.

In the example embodiments of performing video decoding, the input device 650 may receive an encoded bitstream as the input 670. The encoded bitstream may be processed, for example, by the video coding module 625, to generate decoded video data. The decoded video data may be provided via the output device 660 as the output 680.

While this disclosure has been particularly shown and described with references to preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present application as defined by the appended claims. Such variations are intended to be covered by the scope of this present application. As such, the foregoing description of embodiments of the present application is not intended to be limiting.

Claims

A method for video processing, comprising:

performing a conversion between a current video unit of a video and a bitstream of the video, wherein the bitstream comprises information of a downsampling filter for obtaining the current video unit.
The method of claim 1, wherein the information is comprised in a supplemental enhancement information (SEI) message or a video usability information (VUI) message in the bitstream.
The method of claim 1, wherein the information comprises a first indication indicating a type of the downsampling filter.
The method of claim 3, wherein the first indication comprises a syntax element downsampling_filter_type.
The method of any of claims 1-4, wherein the information comprises a second indication indicating an identifying number or an index of the downsampling filter.
The method of claim 5, wherein the second indication comprises a syntax element nnpfc_downsampling_id.
The method of any of claims 3-6, wherein the first indication equal to a first value indicates that the downsampling filter is a neural network-based downsampling filter, or

the first indication equal to a second value indicates that the downsampling filter is a bilinear filter, or

the first indication equal to a third value indicates that the downsampling filter is a bicubic filter, or

the first indication equal to a fourth value indicates that the downsampling filter is a reference picture resampling (RPR) filter.
The method of claim 7, wherein the information comprises a third indication indicates how to determine the downsampling filter.
The method of claim 8, wherein the third indication comprises a syntax element nnpfc_downsampling_mode_idc.
The method of any of claims 8-9, wherein the third indication equal to a fifth value indicates that the downsampling filter is determined based on a pre-defined scheme, or

the third indication equal to a sixth value indicates that the downsampling filter comprises a neural network obtained from the bitstream, or

the third indication equal to a seventh value indicates that the downsampling filter comprises a neural network obtained based on one or more indications in the bitstream, or

the third indication equal to an eighth value indicates that a set of parameters of the downsampling filter is obtained from the bitstream.
The method of claim 10, wherein the one or more indications comprise at least one of a specified tag Uniform Resource Identifier (URI) or a neural network information URI.
The method of any of claims 10-11, wherein the set of parameters is indicated by a fourth indication in the bitstream.
The method of claim 12, wherein the fourth indication comprises a syntax element nnpfc_downsampling_filter_info.
The method of any of claims 10-13, wherein if the first indication is equal to the first value, the third indication is allowed to be equal to one of the fifth value, the sixth value, or the seventh value, or

if the first indication is equal to one of the second value, the third value or the fourth value, the third indication is allowed to be equal to one of the fifth value, or the eighth value.
The method of any of claims 1-14, wherein a value of a first syntax element is consistent with a width of luma sample after applying a post-processing filter identified by a second syntax element, the first syntax element indicates a width of a luma sample array of a video unit resulting by applying the post-processing filter identified by the second syntax element to a decoded current video unit, and the second syntax element indicates an identifying number used to identify the post-processing filter, and

a value of a third syntax element is consistent with a height of luma sample after applying the post-processing filter identified by the second syntax element, the third syntax element indicates a height of a luma sample array of the video unit resulting by applying the post-processing filter identified by the second syntax element to the decoded current video unit.
The method of claim 15, wherein the first syntax element comprises a syntax element nnpfc_pic_width_in_luma_samples, the second syntax element comprises a syntax element nnpfc_id, and the third syntax element comprises a syntax element nnpfc_pic_height_in_luma_samples.
The method of any of claims 1-16, wherein the downsampling filter is a neural network-based downsampling filter, and the bitstream comprises a fifth indication indicating whether at least one indication indicating complexity of the neural network-based downsampling filter is present in the bitstream.
The method of claim 17, wherein the fifth indication comprises a syntax element nnpfc_downsampling_complexity_idc.
The method of any of claims 17-18, wherein the fifth indication equal to a ninth value indicates that the at least one indication is not present in the bitstream, or

the fifth indication equal to a tenth value indicates that the at least one indication is present in the bitstream.
The method of any of claims 1-19, wherein the information comprises a sixth indication specifying the neural network-based downsampling filter.
The method of claim 20, wherein the sixth indication comprises a syntax element nnpfc_downsampling_idc.
The method of any of claims 17-21, wherein the at least one indication comprises a seventh indication indicating a type of parameters of the neural network-based downsampling filter.
The method of claim 22, wherein the seventh indication comprises a syntax element nnpfc_downsampling_parameter_type_idc.
The method of any of claims 22-23, wherein the seventh indication equal to an eleventh value indicates the type of the parameters is integer, or

the seventh indication equal to a twelfth value indicates the type of the parameters is floating point, or

the seventh indication equal to a thirteenth value indicates the type of the parameters is binary.
The method of any of claims 17-25, wherein the at least one indication comprises an eighth indication indicating a bit length of parameters of the neural network-based downsampling filter.
The method of claim 25, wherein the eighth indication comprises a syntax element nnpfc_downsampling_log2_parameter_bit_length_minus3.
The method of any of claims 25-26, wherein the eighth indication equal to a fourteenth value indicates that the bit length of the parameters is smaller than or equal to 8, or

the eighth indication equal to a fifteenth value indicates that the bit length of the parameters is smaller than or equal to 16, or

the eighth indication equal to a sixteenth value indicates that the bit length of the parameters is smaller than or equal to 32, or

the eighth indication equal to a seventeenth value indicates that the bit length of the parameters is smaller than or equal to 64.
The method of any of claims 17-27, wherein the at least one indication comprises a ninth indication indicating the maximum number of parameters of the neural network-based downsampling filter.
The method of claim 28, wherein the ninth indication comprises a syntax element nnpfc_downsampling_num_parameters_idc.
The method of any of claims 17-29, wherein the at least one indication comprises a tenth indication indicating the maximum number of multiply-accumulate operations per sample of the neural network-based downsampling filter.
The method of claim 30, wherein the tenth indication comprises a syntax element nnpfc_downsampling_num_kmac_operations_idc.
The method of any of claims 1-31, wherein a downsampling process is performed at one of the following levels:

a sequence level,

a frame level,

a picture level,

a slice level,

a tile level,

a brick level,

a subpicture level,

a coding transform unit (CTU) level,

a CTU row level,

a level of one or more coding units (CUs) ,

a level of one or more CTUs, or

a level of one or more coding transform blocks (CTBs) .
The method of claim 32, wherein the downsampling process is performed at the frame level with a size of an original resolution for a frame of the video.
The method of any of claims 5-33, wherein the downsampling filter is applied for all color components and pictures of the video, and only one second indication is indicated in the bitstream.
The method of any of claims 1-33, wherein the downsampling filter is comprised in a plurality of downsampling filters, and the plurality of downsampling filters are applied for different video units of the video.
The method of any of claims 1-33, wherein the downsampling filter is comprised in a plurality of downsampling filters, and the plurality of downsampling filters are applied for different color components of the video.
The method of claim 36, wherein the different color components comprise a first color component, a second color component and a third color component, a plurality of eleventh indications are signaled in an order of the first color component, the second color component and the third color component, and an eleventh indication indicates an identifying number or an index of one of the plurality of downsampling filters.
The method of claim 37, wherein the eleventh indication comprises a syntax element nnpfc_downsampling_id.
The method of claim 36, wherein the different color components comprise a first color component, a second color component and a third color component, a twelfth indication, a thirteenth indication and a fourteenth indication are indicated in the bitstream, the twelfth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the first color component, the thirteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the second color component, and the fourteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the third color component.
The method of claim 39, wherein the twelfth indication comprises a syntax element nnpfc_downsampling_id_y, the thirteenth indication comprises a syntax element nnpfc_downsampling_id_u, and the fourteenth indication comprises a syntax element nnpfc_downsampling_id_v.
The method of any of claims 37-40, wherein the first color component is color component Y, the second color component is color component U, and the third color component is color component V.
The method of any of claims 1-41, wherein the downsampling filter is comprised in a plurality of downsampling filters, and the plurality of downsampling filters are applied for different picture types of the video.
The method of claim 42, wherein the different picture types comprise a first picture type, a second picture type and a third picture type, a plurality of fifteenth indications are signaled in an order of the first picture type, the second picture type and the third picture type, and a fifteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters.
The method of claim 43, wherein the fifteenth indication comprises a syntax element nnpfc_downsampling_id.
The method of claim 42, wherein the different picture types comprise a first picture type, a second picture type and a third picture type, a sixteenth indication, a seventeenth indication and an eighteenth indication are indicated in the bitstream, the sixteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the first picture type, the seventeenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the second picture type, and the eighteenth indication indicates an identifying number or an index of one of the plurality of downsampling filters that is applied for the third picture type.
The method of claim 45, wherein the sixteenth indication comprises a syntax element nnpfc_downsampling_id_I, the seventeenth indication comprises a syntax element nnpfc_downsampling_id_P, and the eighteenth indication comprises a syntax element nnpfc_downsampling_id_B.
The method of any of claims 43-46, wherein the first picture type is I slice, the second picture type is P slice, and the third picture type is B slice.
The method of any of claims 1-47, wherein the bitstream further comprises a nineteenth indication and a twentieth indication, the nineteenth indication indicates a width scaling factor of a post-processing filter for processing a reconstruction of the current video unit, and the twentieth indication indicates a length scaling factor of the post-processing filter.
The method of claim 48, wherein the nineteenth indication comprises a syntax element nnpfc_scaling_factor_width, and the twentieth indication comprises a syntax element nnpfc_scaling_factor_height.
The method of any of claims 48-49, wherein the post-processing filter is identified by a syntax element nnpfc_id.
The method of any of claims 48-50, wherein the bitstream further comprises a twenty-first indication and a twenty-second indication, the twenty-first indication indicates a width of a luma sample array of a video unit resulting by applying the post-processing filter to a decoded current video unit, and the twenty-second indication indicates a height of the luma sample array of the video unit resulting by applying the post-processing filter to the decoded current video unit.
The method of claim 51, wherein the twenty-first indication comprises a syntax element nnpfc_pic_width_in_luma_samples, and the twenty-second indication comprises a syntax element nnpfc_pic_height_in_luma_samples.
The method of any of claims 51-52, wherein a value of the nineteenth indication is consistent with a value of the twenty-first indication, and a value of the twentieth indication is consistent with a value of the twenty-second indication.
The method of claim 53, wherein a product of the value of the nineteenth indication and a width of the current video unit is equal to the value of the twenty-first indication.
The method of any of claims 53-54, wherein a product of the value of the twentieth indication and a height of the current video unit is equal to the value of the twenty-second indication.
The method of any of claims 51-52, wherein if a value of the nineteenth indication is not consistent with a value of the twenty-first indication and a value of the twentieth indication is not consistent with a value of the twenty-second indication, a plurality of upsampling processes are performed on the reconstruction of the current video unit by using the post-processing filter.
The method of any of claims 51-52, wherein if a value of the nineteenth indication is not consistent with a value of the twenty-first indication and a value of the twentieth indication is not consistent with a value of the twenty-second indication, a bilinear filter or a bicubic filter is applied to the reconstruction of the current video unit in combination with the post-processing filter.
The method of any of claims 48-50, wherein a twenty-first indication and a twenty-second indication are absent from the bitstream, the twenty-first indication indicates a width of a luma sample array of a video unit resulting by applying the post-processing filter to a decoded current video unit, and the twenty-second indication indicates a height of the luma sample array of the video unit resulting by applying the post-processing filter to the decoded current video unit.
The method of claim 58, wherein the twenty-first indication comprises a syntax element nnpfc_pic_width_in_luma_samples, and the twenty-second indication comprises a syntax element nnpfc_pic_height_in_luma_samples.
The method of any of claims 58-59, wherein the width of the luma sample array is determined based on a value of the nineteenth indication and a width of the current video unit, and the height of the luma sample array is determined based on a value of the twentieth indication and a height of the current video unit.
The method of any of claims 58-60, wherein the luma sample array is indicted in the bitstream.
The method of any of claims 58-61, wherein the width of the luma sample array and the height of the luma sample array are indicated in the bitstream.
The method of claim 62, wherein the width of the luma sample array is indicated by a twenty-third indication.
The method of claim 63, wherein the twenty-third indication comprises a syntax element nnpfc_scaled_pic_width_in_luma_samples.
The method of any of claims 63-64, wherein a value of the twenty-third indication is equal to a product of the value of the nineteenth indication and a width of the current video unit.
The method of any of claims 62-65, wherein the height of the luma sample array is indicated by a twenty-fourth indication.
The method of claim 66, wherein the twenty-fourth indication comprises a syntax element nnpfc_scaled_pic_height_in_luma_samples.
The method of any of claims 66-67, wherein a value of the twenty-fourth indication is equal to a product of the value of the twentieth indication and a height of the current video unit.
The method of any of claims 1-68, wherein the conversion includes encoding the current video unit into the bitstream.
The method of any of claims 1-68, wherein the conversion includes decoding the current video unit from the bitstream.
An apparatus for video processing comprising a processor and a non-transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform a method in accordance with any of claims 1-70.
A non-transitory computer-readable storage medium storing instructions that cause a processor to perform a method in accordance with any of claims 1-70.
A non-transitory computer-readable recording medium storing a bitstream of a video which is generated by a method performed by an apparatus for video processing, wherein the method comprises:

performing a conversion between a current video unit of the video and the bitstream, wherein the bitstream comprises information of a downsampling filter for obtaining the current video unit.
A method for storing a bitstream of a video, comprising:

performing a conversion between a current video unit of the video and the bitstream, wherein the bitstream comprises information of a downsampling filter for obtaining the current video unit; and

storing the bitstream in a non-transitory computer-readable recording medium.