Method and device for video processing and medium

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is presented. The method includes performing a conversion between a current video unit of the video and a bitstream of the video, where the bitstream includes a first indication that is allowed to activate a target neural network post-processing filter (NNPF), the target NNPF being applied to a plurality of video units of the video.

Description

Cross-references to related applications

[0001] This application claims priority to U.S. Provisional Patent Application No. 63 / 404,927, filed on September 8, 2022, the entire contents of which are incorporated herein by reference. Technical Field

[0002] Embodiments of the present disclosure relate generally to video processing techniques, and more particularly, to neural network post-filter activation. Background Art

[0003] Nowadays, digital video capabilities are being applied to all aspects of people's lives. For video encoding / decoding, various types of video compression technologies have been proposed, such as MPEG-2, MPEG-4, ITU-TH.263, ITU-TH.264 / MPEG-4 Part 10 Advanced Video Codec (AVC), ITU-TH.265 High Efficiency Video Codec (HEVC) standard, and Versatile Video Codec (VVC) standard. However, it is generally expected to further improve the encoding and decoding efficiency of video encoding and decoding technologies. Summary of the invention

[0004] Embodiments of the present disclosure provide a solution for video processing.

[0005] In a first aspect, a method for video processing is provided. The method comprises: performing a conversion between a current video unit of a video and a bitstream of the video, wherein the bitstream comprises a first indication that a target neural network post-processing filter (NNPF) is enabled to be activated, the target NNPF being applied to a plurality of video units of the video.

[0006] According to the method of the first aspect of the present disclosure, a first indication in a bitstream is allowed to activate a target NNPF to be applied to multiple video units. Compared to conventional solutions in which the activation indication only maintains a single video unit, the proposed method can advantageously reduce the number of indications required to transmit activation information through a signal, and thus the coding efficiency can be improved.

[0007] In a second aspect, a device for video processing is provided. The device includes a processor and a non-volatile memory having instructions thereon. The instructions, when executed by the processor, cause the processor to perform the method according to the first aspect of the present disclosure.

[0008] In a third aspect, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores instructions for causing a processor to execute the method according to the first aspect of the present disclosure.

[0009] In a fourth aspect, another non-transitory computer-readable recording medium is provided. The non-transitory computer-readable recording medium stores a bitstream of a video generated by a method performed by an apparatus for video processing. The method includes: performing a conversion between a current video unit of the video and a bitstream, wherein the bitstream includes a first indication that a target neural network post-processing filter (NNPF) is allowed to be activated, and the target NNPF is applied to multiple video units of the video.

[0010] In a fifth aspect, a method for storing a bitstream of a video is provided. The method includes: performing a conversion between a current video unit of the video and a bitstream, wherein the bitstream includes a first indication that a target neural network post-processing filter (NNPF) is allowed to be activated, and the target NNPF is applied to multiple video units of the video; and storing the bitstream in a non-transitory computer-readable recording medium.

[0011] 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

[0012] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become more apparent through the following detailed description with reference to the accompanying drawings. In the exemplary embodiments of the present disclosure, the same reference numerals generally refer to the same components.

[0013] Figure 1 A block diagram illustrating an example video encoding and decoding system is shown according to some embodiments of the present disclosure;

[0014] Figure 2 A block diagram illustrating a first example video encoder is shown according to some embodiments of the present disclosure;

[0015] Figure 3 shows a block diagram illustrating an example video decoder according to some embodiments of the present disclosure;

[0016] Figure 4 is an example illustration of the brightness data channel;

[0017] Figure 5 A flowchart showing a method for video processing according to an embodiment of the present disclosure; and

[0018] Figure 6 A block diagram of a computing device is shown in which various embodiments of the present disclosure may be implemented.

[0019] Throughout the drawings, the same or similar reference numbers generally refer to the same or similar elements. DETAILED DESCRIPTION

[0020] The principle of the present disclosure will now be described with reference to some embodiments. It should be understood that these embodiments are described only for the purpose of illustrating and helping those skilled in the art to understand and implement the present disclosure, without implying any limitation on the scope of the present disclosure. In addition to the methods described below, the disclosure described herein can also be implemented in various ways.

[0021] 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 skill in the art to which this disclosure belongs.

[0022] References in this disclosure to "one embodiment," "an embodiment," "an example embodiment," and the like indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment must include the particular feature, structure, or characteristic. Furthermore, these phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an example embodiment, it is claimed that such feature, structure, or characteristic, whether or not explicitly described, is within the knowledge of those skilled in the art to affect correlation with other embodiments.

[0023] It should be understood that, although the terms "first" and "second" etc. may be used herein to describe various elements, these elements should not be limited to these terms. These terms are only used to distinguish one element from another element. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element without departing from the scope of the exemplary embodiments. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0024] The terms used herein are only used for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments. As used herein, the singular forms "a", "an" and "the" are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the terms "include", "comprises", "has", "has", "includes" and / or "comprising" are used herein to indicate the presence of the features, elements and / or components, etc., but do not exclude the presence or addition of one or more other features, elements, components and / or combinations thereof. Example Environment

[0025] Figure 11 is a block diagram illustrating an example video codec system 100 that may utilize the techniques of the present disclosure. As shown, the video codec system 100 may include a source device 110 and a destination device 120. The source device 110 may also be referred to as a video encoding device, and the destination device 120 may also be referred to as a video decoding device. In operation, the source device 110 may be configured to generate encoded video data, and the destination device 120 may 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.

[0026] The video source 112 may include a source such as a video acquisition device. Examples of a video acquisition device include, but are not limited to, an interface for receiving video data from a video content provider, a computer graphics system for generating video data, and / or a combination thereof.

[0027] The video data may include 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 bit sequence that forms a coded representation of the video data. The bitstream may include coded pictures and associated data. The coded pictures are coded representations of pictures. The associated data may include sequence parameter sets, picture parameter sets, and other grammatical structures. The I / O interface 116 may include a modulator / demodulator and / or a transmitter. The coded video data may be directly transmitted to the destination device 120 via the network 130A via the I / O interface 116. The coded video data may also be stored on a storage medium / server 130B for access by the destination device 120.

[0028] 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 obtain 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 the user. The display device 122 may be integrated with the destination device 120, or may be outside the destination device 120, which is configured to be connected to an external display device interface.

[0029] The video encoder 114 and the video decoder 124 may operate according to a video compression standard, such as the High Efficiency Video Codec (HEVC) standard, the Versatile Video Codec (VVC) standard, and other existing and / or future standards.

[0030] Figure 2is a block diagram showing an example of a video encoder 200 according to some embodiments of the present disclosure, which may be Figure 1 An example of a video encoder 114 in the system 100 is shown.

[0031] Video encoder 200 may be configured to implement any or all of the techniques of this disclosure. Figure 2 In the example of , video encoder 200 includes multiple functional components. The techniques described in this disclosure can be shared between the various components of video encoder 200. In some examples, a processor can be configured to perform any or all of the techniques described in this disclosure.

[0032] In some embodiments, the video encoder 200 may include a partitioning unit 201, a prediction unit 202, a residual generation unit 207, a transformation unit 208, a quantization unit 209, an inverse quantization unit 210, an inverse transformation unit 211, a reconstruction unit 212, a buffer 213 and an entropy coding unit 214, and the prediction unit 202 may include a mode selection unit 203, a motion estimation unit 204, a motion compensation unit 205 and an intra-frame prediction unit 206.

[0033] In other examples, the video encoder 200 may include more, fewer, or different functional components. In one example, the prediction unit 202 may include an intra-block copy (IBC) unit. The IBC unit may perform prediction in an IBC mode in which at least one reference picture is a picture in which the current video block is located.

[0034] Furthermore, although some components (such as the motion estimation unit 204 and the motion compensation unit 205) may be integrated, for the purpose of explanation, these components are described in detail below. Figure 2 are shown separately in the example.

[0035] The partitioning 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.

[0036] The mode selection unit 203 may select one of a plurality of encoding modes (intra-frame encoding or inter-frame encoding), for example, based on the error result, and provide the generated intra-frame encoded block or inter-frame encoded block to the residual generation unit 207 to generate residual block data, and to the reconstruction unit 212 to reconstruct the encoded block for use as a reference picture. In some examples, the mode selection unit 203 may select an intra-frame inter-frame joint prediction (CIIP) mode, in which the prediction is based on an inter-frame prediction signal and an intra-frame prediction signal. In the case of inter-frame prediction, the mode selection unit 203 may also select a resolution for a motion vector (e.g., sub-pixel precision or integer pixel precision) for the block.

[0037] To perform inter-frame prediction on the current video block, the motion estimation unit 204 may generate motion information for the current video block by comparing the current video block with one or more reference frames from the buffer 213. 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.

[0038] The motion estimation unit 204 and the motion compensation unit 205 may perform different operations on the current video block, for example, depending on whether the current video block is in an I slice, a P slice, or a B slice. As used herein, an "I slice" may refer to a portion of a picture consisting of macroblocks, all of which are based on macroblocks within the same picture. Furthermore, as used herein, in some aspects, a "P slice" and a "B slice" may refer to a portion of a picture consisting of macroblocks that are independent of macroblocks in the same picture.

[0039] In some examples, the motion estimation unit 204 may perform unidirectional prediction on the current video block, and the motion estimation unit 204 may search the reference pictures of list 0 or list 1 to find the reference video block for the current video block. The motion estimation unit 204 may then generate a reference index and a motion vector, the reference index indicating the reference picture in list 0 or list 1 containing the reference video block, and the motion vector indicating the spatial displacement between the current video block and the reference video block. The motion estimation unit 204 may output the reference index, the prediction direction indicator, and the motion vector as the motion information of the current video block. The motion compensation unit 205 may generate a predicted video block for the current video block based on the reference video block indicated by the motion information of the current video block.

[0040] Alternatively, in other examples, the motion estimation unit 204 may perform bidirectional prediction on the current video block. The motion estimation unit 204 may search the reference pictures in list 0 to find a reference video block for the current video block, and may also search the reference pictures in list 1 to find another reference video block for the current video block. The motion estimation unit 204 may then generate a plurality of reference indexes and a plurality of motion vectors, the plurality of reference indexes indicating a plurality of reference pictures in list 0 and list 1 containing a plurality of reference video blocks, and the plurality of motion vectors indicating a plurality of spatial displacements between the plurality of reference video blocks and the current video block. The motion estimation unit 204 may output the plurality of reference indexes and the plurality of motion vectors of the current video block as motion information of the current video block. The motion compensation unit 205 may generate a predicted video block for the current video block based on the plurality of reference video blocks indicated by the motion information of the current video block.

[0041] In some examples, motion estimation unit 204 may output a complete set of motion information for use in a decoding process by a decoder. Alternatively, in some embodiments, motion estimation unit 204 may signal motion information of a current video block with reference to motion information of another video block. For example, motion estimation unit 204 may determine that motion information of a current video block is sufficiently similar to motion information of a neighboring video block.

[0042] In one example, motion estimation unit 204 may indicate a value in a syntax structure associated with the current video block that indicates to video decoder 300 that the current video block has the same motion information as another video block.

[0043] In another example, the motion estimation unit 204 may identify another video block and a motion vector difference (MVD) in a syntax structure associated with the current video block. The motion vector difference indicates the difference between the motion vector of the current video block and the motion vector of the indicated video block. The video decoder 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.

[0044] As discussed above, the video encoder 200 may signal motion vectors in a predictive manner.Two examples of prediction signaling techniques that may be implemented by the video encoder 200 include Advanced Motion Vector Prediction (AMVP) and merge mode signaling.

[0045] 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 prediction video block and various syntax elements.

[0046] The residual generation unit 207 may generate residual data for the current video block by subtracting (e.g., indicated by a minus sign) the prediction 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 corresponding to different sample components of samples in the current video block.

[0047] In other examples, such as in skip mode, there may be no residual data for the current video block, and the residual generation unit 207 may not perform a subtraction operation.

[0048] Transform processing unit 208 may generate one or more transform coefficient video blocks for a current video block by applying one or more transforms to the residual video block associated with the current video block.

[0049] After transform processing unit 208 generates a transform coefficient video block associated with the current video block, 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.

[0050] The inverse quantization unit 210 and the inverse transform unit 211 may apply inverse quantization and inverse transform to the transform coefficient video block, respectively, to reconstruct a residual video block from the transform coefficient video block. The reconstruction unit 212 may add the reconstructed residual video block to corresponding samples from one or more prediction video blocks generated by the prediction unit 202 to generate a reconstructed video block associated with the current video block for storage in the buffer 213.

[0051] After reconstruction unit 212 reconstructs the video block, a loop filtering operation may be performed to reduce video blocking artifacts in the video block.

[0052] 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 including the entropy-encoded data.

[0053] Figure 3 is a block diagram showing an example of a video decoder 300 according to some embodiments of the present disclosure, which may be Figure 1 An example of a video decoder 124 in the system 100 is shown.

[0054] Video decoder 300 may be configured to perform any or all of the techniques of this disclosure. Figure 3 In the example of , video decoder 300 includes multiple functional components. The techniques described in this disclosure can be shared between the various components of video decoder 300. In some examples, a processor can be configured to perform any or all of the techniques described in this disclosure.

[0055] exist Figure 3 In the example of , 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 transform unit 305, and a reconstruction unit 306 and a buffer 307. In some examples, the video decoder 300 can perform a decoding process that is generally opposite to the encoding process described with respect to the video encoder 200.

[0056] The entropy decoding unit 301 can retrieve the encoded bitstream. The encoded bitstream may include entropy encoded video data (e.g., encoded blocks of video data). The entropy decoding unit 301 can decode the entropy encoded video data, and the motion compensation unit 302 can determine motion information from the entropy decoded video data, the motion information including motion vectors, motion vector precision, reference picture list indexes, and other motion information. The motion compensation unit 302 can determine such information, for example, by performing AMVP and merge mode. AMVP is used, including deriving several most likely candidates based on data and reference pictures from neighboring PBs. The motion information typically includes horizontal motion vector displacement values ​​and vertical motion vector displacement values, one or two reference picture indexes, and in the case of prediction areas in B stripes, also includes an identification of which reference picture list is associated with each index. As used herein, in some aspects, "merge mode" may refer to deriving motion information from spatially neighboring blocks or temporally neighboring blocks.

[0057] The motion compensation unit 302 may generate motion compensated blocks, possibly performing interpolation based on interpolation filters.Identifiers for the interpolation filters used with sub-pixel precision may be included in the syntax elements.

[0058] The motion compensation unit 302 may calculate interpolated values ​​for sub-integer pixels of a reference block using interpolation filters used by the video encoder 200 during encoding of the video block. The motion compensation unit 302 may determine the interpolation filters used by the video encoder 200 based on received syntax information, and the motion compensation unit 302 may use the interpolation filters to generate a prediction block.

[0059] The motion compensation unit 302 may use at least part of the syntax information to determine the size of blocks used to encode (multiple) frames and / or (multiple) slices of the encoded video sequence, partition information describing how each macroblock of a picture of the encoded video sequence is partitioned, a mode indicating how each partition is encoded, one or more reference frames (and reference frame lists) for each inter-coded block, and other information for decoding the encoded video sequence. As used herein, in some aspects, a "slice" may refer to a data structure that can be decoded independently of other slices of the same picture in terms of entropy coding and decoding, signal prediction, and residual signal reconstruction. A slice may be an entire picture, or it may be a region of a picture.

[0060] The intra prediction unit 303 may use, for example, an intra prediction mode received in the bitstream to form a prediction block from spatially neighboring blocks. The inverse quantization unit 304 inverse quantizes (i.e., dequantizes) the quantized video block coefficients provided in the bitstream and decoded by the entropy decoding unit 301. The inverse transform unit 305 applies an inverse transform.

[0061] The reconstruction unit 306 may obtain the decoded block, for example, by adding the residual block to the corresponding prediction block generated by the motion compensation unit 302 or the intra prediction unit 303. If necessary, a deblocking filter may also be applied to filter the decoded block to remove blocking artifacts. The decoded video block is then stored in a buffer 307, which provides reference blocks for subsequent motion compensation / intra prediction, and the buffer 307 also generates the decoded video for presentation on a display device.

[0062] Some exemplary embodiments of the present disclosure will be described in detail below. It should be noted that the section titles used in this document are for ease of understanding, and the embodiments disclosed in the section are not limited to the section. In addition, although some embodiments are described with reference to general video codecs or other specific video codecs, the disclosed technology is also applicable to other video coding and decoding technologies. In addition, although some embodiments describe the video encoding steps in detail, it should be understood that the corresponding decoding steps of de-encoding will be implemented by the decoder. In addition, the term video processing includes video encoding or compression, video decoding or decompression, and video transcoding, in which video pixels are represented from one compression format to another compression format or at different compression bit rates. 1. Brief Overview The present disclosure relates to image / video coding techniques. In particular, the present disclosure relates to activation of a neural network post-processing filter for samples of a group of consecutive pictures or a group of pictures with the same parameters (e.g., quantization parameters, temporal layer ids, picture types), or a group of pictures associated with the same color components. The concepts can be applied individually or in various combinations for video bitstreams encoded and decoded by any codec (e.g., the generic video codec (VVC) standard and / or the generic SEI message (VSEI) standard for encoded and decoded video bitstreams). 2. Abbreviations APS Adaptive Parameter Set AU Access Unit CLVS Codec layer video sequence CLVSS coded layer video sequence starts CRC Cyclic Redundancy Check CVS Codec Video Sequence FIR Finite Impulse Response IRAP Intra-frame random access point NAL Network Abstraction Layer PPS Picture Parameter Set PU Picture Unit RASL Random Access Skip Preamble SEI Supplemental Enhancement Information STSA Stepped Temporal Sublayer Access VCL video codec layer VSEI Generic Supplementary Enhancement Information (Rec.ITU-T H.274|ISO / IEC 23002-7) VUI Video Availability Information VVC Universal Video Codec (Rec.ITU-T H.266|ISO / IEC 23090-3) 3. Introduction 3.1. Video Codec Standards Video codec standards have evolved primarily through the development of the well-known ITU-T and ISO / IEC standards. ITU-T developed H.261 and H.263, ISO / IEC developed MPEG-1 and MPEG-4 Vision, and the two organizations jointly developed H.262 / MPEG-2 Video and H.264 / MPEG-4 Advanced Video Codec (AVC) and H.265 / HEVC standards. Since H.262, video codec standards have been based on a hybrid video codec structure, where temporal prediction plus transform codecs are used. In order to explore future video codec technologies after HEVC, the Joint Video Exploration Team (JVET) was jointly established by VCEG and MPEG in 2015. Since then, JVET has adopted many new methods and put them into reference software called Joint Exploration Model (JEM). When the Versatile Video Codec (VVC) project officially started, JVET was later renamed the Joint Video Experts Group (JVET). VVC is a new codec standard that aims to reduce bit rate by 50% compared to HEVC. The standard has been finalized by JVET at the 19th JVET meeting that ended on July 1, 2020. The Versatile Video Codec (VVC) standard (ITU-T H.266 | ISO / IEC 23090-3) and the associated Versatile Supplementary Enhancement Information (VSEI) standard for coded video bitstreams (ITU-T H.274 | ISO / IEC23002-7) have been designed for the widest range of applications, including traditional uses such as television broadcasting, video conferencing or playback from storage media, as well as newer and more advanced use cases such as adaptive bitrate streaming, video region extraction, composition and merging of content from multiple coded video bitstreams, multi-view video, scalable layered codecs, and viewport-adaptive 360° immersive media. The Essential Video Codec (EVC) standard (ISO / IEC 23094-1) is another video codec standard that has been recently developed by MPEG. 3.2. General SEI messages and SEI messages in VVC and VSEI SEI messages assist processes related to decoding, display, or other purposes. However, SEI messages are not required for constructing luma or chroma samples through the decoding process. A compliant decoder does not need to process this information in order to comply with the output order. Some SEI messages are required for checking bitstream compliance and output timing decoder compliance. Other SEI messages are not required for checking bitstream compliance. Annex D of VVC specifies the syntax and semantics of SEI message payloads for some SEI messages, and specifies the use of SEI messages and VUI parameters for which syntax and semantics are specified in ITU-T H.274 | ISO / IEC 23002-7. 3.3. Signaling of neural network post-filters The existing design includes the specification of two SEI messages for signaling a neural network post-filter, as follows. 4. Question The current design of the Neural Network Post-Filter Activation (NNPFA) SEI message has the following problems: 1) The NNPFA SEI message specifies a neural network post-processing filter that can be used for post-processing filtering of the current picture. The NNPFA SEI message is maintained only for the current picture. However, this is inefficient when a specific filter is applied to a group of consecutive pictures in decoding order or output order. 5. Detailed solution In order to solve the above problems, the methods outlined below are disclosed. The solutions should be considered as examples to explain the general concept and should not be interpreted in a narrow way. In addition, these solutions can be applied individually or in combination in any way. In the following description, the term "picture" can be replaced by any video unit, such as "slice". The term "consecutive video units in output / decoding order" can be replaced by "a group of video units with the same parameters (e.g., picture-level quantization parameter, picture type, temporal layer id) in output order". 1) In one method, activation of a neural network based (NN-based) operation (such as a NN-based post-processing filter) for a group of consecutive video units (such as pictures or slices) in output order is achieved by adding an indication to a neural network post-filter activation (NNPFA) SEI message, wherein the indication is used to indicate the activation or deactivation of the neural network post-processing filter. a. In one example, nnpfa_id is specified to specify a target neural network post-processing filter specified by one or more neural network post-filter characteristics (NNPFC) SEI messages associated with the current video unit and having nnpfc_id equal to nnfpa_id. b. In one example, specifying an NNPFA SEI message activates or deactivates possible usage of a target neural network post-processing filter for post-processing filtering of a set of video units. c. In one example, the additional indication is signaled via an additional flag named nnpfa_on_flag, and one or more of the following applies: i. In one example, for nnpfa_on_flag equal to 1, the following semantics are specified: nnpfa_on_flag equal to 1 specifies that the target neural network post-processing filter can be used for post-processing filtering for the current video unit and all subsequent video units of the current layer in output order until one or more of the following conditions are true: - A new CLVS starts for the current layer. - End of bitstream. - the video unit in the current layer that is associated with an NNPFA SEI message with nnpfa_on_flag equal to 0 and the same nnpfa_id as the current SEI message is output, This video unit follows the current video unit in the output order. Note - The target neural network post-processing filters are not applied to the current layer with a NNPFA SEI For this subsequent picture associated with the message, the NNPFA SEI message has nnpfa_on_flag equal to 0 and the same nnpfa_id as the current SEI message. ii. In one example, specifying nnpfa_on_flag equal to 0 specifies that maintenance of the target neural network post-processing filter is canceled, i.e., the target neural network post-processing filter is no longer used unless the target neural network post-processing filter is activated by another NNPFA SEI message with nnpfa_on_flag equal to 1 and the same nnpfa_id as the current SEI message. 2) In one method, activation of NN-based operations (e.g., post-processing filters) for a group of consecutive video units in decoding order is achieved by adding an indication to an NNPFA SEI message, wherein the following aspects differ from the method specified by item 1 and its sub-items above (other aspects are the same): a. In one example, the additional indication is signaled via an additional flag named nnpfa_on_flag, and one or more of the following applies: i. In one example, for nnpfa_on_flag equal to 1, the following semantics are specified: nnpfa_on_flag equal to 1 specifies that the target neural network post-processing filter can be used for post-processing filtering for the current video unit and all subsequent video units of the current layer in decoding order until one or more of the following conditions are true: - A new CLVS starts for the current layer. - End of bitstream. - A picture in the current layer associated with an NNPFA SEI message with nnpfa_on_flag equal to 0 and the same nnpfa_id as the current SEI message is decoded, and the picture follows the current picture in decoding order. Note - The target neural network post-processing filters are not applied to the current layer with a NNPFA SEI For this subsequent picture associated with the message, the NNPFA SEI message has nnpfa_on_flag equal to 0 and the same nnpfa_id as the current SEI message. 3) In one approach, activation of NN-based operations (e.g., neural network post-processing filters) for a set of consecutive pictures in output order is enabled by adding a new SEI message for deactivating the neural network post-processing filters. a. In one example, the new SEI message is named Neural Network Post Filter Deactivation (NNPFD) SEI message, where the syntax only contains the ue(v) codec syntax element nnpfd_id. b. In one example, nnpfd_id is specified to specify a target neural network post-processing filter specified by one or more neural network post-processing filter characteristics (NNPFC) SEI messages associated with the current picture and having nnpfc_id equal to nnfpd_id. i. Alternatively, instead of signaling one target neural network post-processing filter, multiple target neural network post-processing filters may be indicated in the NNPFD SEI message. 1. Alternatively, moreover, multiple instances of nnpfd_id may be signaled. c. In one example, specifying an NNPFD SEI message deactivates possible use of a target neural network post-processing filter specified by nnpfd_id. Once a target neural network post-processing filter is deactivated, the target neural network post-processing filter is no longer used unless the target neural network post-processing filter is activated again by a subsequent NNPFA SEI message in decoding order, the nnpfa_id of the NNPFA SEI message being equal to the nnpfd_id of the current SEI message. d. In one example, specifying an NNPFA SEI message activates possible use of a target neural network post-processing filter specified by nnpfa_id for post-processing filtering of a set of pictures. e. In one example, nnpfa_id is specified to specify a target neural network post-processing filter specified by one or more neural network post-filter characteristics (NNPFC) SEI messages associated with the current picture and having nnpfc_id equal to nnfpa_id. f. In one example, the following is specified as part of the semantics of the NNPFA SEI message: The target neural network post-processing filter can be used for post-processing filtering for the current picture and all subsequent pictures of the current layer in output order until one or more of the following conditions are true: - A new CLVS starts for the current layer. - End of bitstream. - The picture in the current layer that is associated with the neural network post filter deactivation (NNPFD) SEI message with nnpfd_id equal to nnpfa_id is output, which picture follows the current picture in the output order. NOTE—The target neural network post-processing filter is not applied to this subsequent picture in the current layer that is associated with a NNPFD SEI message with nnpfd_id equal to nnpfa_id. 4) In one method, activation of NN-based operations (e.g., post-processing filters) for a set of consecutive pictures in decoding order is achieved by adding a new SEI message for deactivating NN-based operations, wherein the following aspects are different from the method specified by item 3 and its sub-items above (other aspects are the same): a. In one example, the following is specified as part of the semantics of the NNPFA SEI message: The target neural network post-processing filter can be used to decode the current picture and the current layer. All subsequent pictures in the sequence are post-processed until one or more of the following conditions are true: - A new CLVS starts for the current layer. - End of bitstream. - A picture in the current layer associated with a neural network post filter deactivation (NNPFD) SEI message with nnpfd_id equal to nnpfa_id is decoded, which picture follows the current picture in decoding order. NOTE—The target neural network post-processing filter is not applied to this subsequent picture in the current layer that is associated with a NNPFD SEI message with nnpfd_id equal to nnpfa_id. 5) In one method, activation of NN-based operations (such as post-processing filters) for a set of consecutive pictures in output order is achieved by adding two indications to the NN-based operation activation (NNPFA) SEI message, one indication being used to indicate whether to cancel the maintenance of the neural network post-processing filter, and the other indication being used to indicate the maintenance of the NN-based operation. a. In one example, nnpfa_id is specified to specify a target neural network post-processing filter specified by one or more neural network post-filter characteristics (NNPFC) SEI messages associated with the current picture and having nnpfc_id equal to nnfpa_id. b. In one example, specifying an NNPFA SEI message activates or deactivates possible use of a target neural network post-processing filter for post-processing filtering of a set of pictures. c. In one example, the two additional flags are named nnpfa_cancel_flag and nnpfa_persistence_flag, and nnpfa_persistence_flag is present only when nnpfa_cancel_flag is equal to 0, and one or more of the following applies: i. In one example, nnpfa_cancel_flag equal to 1 is specified to indicate that the maintenance of the target neural network post-processing filter established by any previous NNPFA SEI message with the same nnpfa_id as the current SEI message is canceled, i.e., the target neural network post-processing filter is no longer used unless it is activated by another NNPFA SEI message with the same nnpfa_id as the current SEI message and nnpfa_cancel_flag equal to 0. nnpfa_cancel_flag equal to 0 indicates that nnpfa_persist- tence_flag comes after nnpfa_cancel_flag. ii. In one example, for nnpfa_persistence_flag, the following semantics are specified: nnpfa_persistence_flag specifies persistence of the target neural network post-processing filters for the current layer. nnpfa_persistence_flag equal to 0 specifies that the target neural network post-processing filter can be used for post-processing filtering of the current picture only. nnpfa_persistence_flag equal to 1 specifies that the target neural network post-processing filter can be used for post-processing filtering for the current picture and all subsequent pictures of the current layer in output order until one or more of the following conditions are true: - A new CLVS starts for the current layer. - End of bitstream. - A picture in the current layer that is associated with an NNPFA SEI message with the same nnpfa_id as the current SEI message and nnpfa_cancel_flag equal to 1 is output, and the picture follows the current picture in the output order. NOTE—The target neural network post-processing filter is not applied to this subsequent picture in the current layer that is associated with an NNPFA SEI message with the same nnpfa_id and nnpfa_cancel_flag equal to 1 as the current SEI message. 6) In one method, activation of a NN-based operation (such as a post-processing filter) for a group of consecutive pictures in decoding order is achieved by adding two indications to a NN-based operation activation (NNPFA) SEI message, one indication for indicating whether to cancel the maintenance of the NN-based operation, and the other indication for indicating the maintenance of the NN-based operation, wherein the following aspects are different from the method specified by item 5 and its sub-items above (other aspects are the same): a. In one example, two indications are named nnpfa_cancel_flag and Two additional flags, nnpfa_persistence_flag, are signaled, and nnpfa_persis- tence_flag is only present when nnpfa_cancel_flag is equal to 0 and the following applies: i. In one example, for nnpfa_persistence_flag, the following semantics are specified: nnpfa_persistence_flag specifies persistence of the target neural network post-processing filters for the current layer. nnpfa_persistence_flag equal to 0 specifies that the target neural network post-processing filter can be used for post-processing filtering of the current picture only. nnpfa_persistence_flag equal to 1 specifies that the target neural network post-processing filter can be used for post-processing filtering for the current picture and all subsequent pictures of the current layer in decoding order until one or more of the following conditions are true: - A new CLVS starts for the current layer. - End of bitstream. - a picture in the current layer associated with an NNPFA SEI message with the same nnpfa_id as the current SEI message and nnpfa_cancel_flag equal to 1 is decoded, This picture follows the current picture in decoding order. Note - The target neural network post-processing filters are not applied to the current layer with a NNPFA SEI For this subsequent picture associated with the message, the NNPFA SEI message has the same nnpfa_id as the current SEI message and nnpfa_cancel_flag equal to 1. 7) In one approach, how to interpret activation messages of NN-based operations (eg, post-processing filters) signaled in SEI messages for video units (eg, pictures) may depend on the codec information of the video units. a. For example, the SEI message can be for I slices (I pictures) and P slices (pictures) or B slices (pictures) Interpreted in different ways. b. For example, SEI messages may be interpreted differently for video units with different QPs. c. For example, SEI messages may be interpreted differently for lossless coded or lossy coded video units. 8) In one method, the number of consecutive video units (eg, pictures or a group of pictures with certain properties) in output order to which NN-based operations (such as post-processing filters) may be applied is signaled in the NNPFA SEI message. 9) In one method, the number of consecutive video units (eg, pictures or a group of pictures with certain properties) in decoding order to which NN-based operations (such as post-processing filters) may be applied is signaled in the NNPFA SEI message. 6. Examples Below are some example embodiments for the case where, for Solution Item 1, Solution Item 3, Solution Item 5 and their sub-items outlined in Section 5 above, the video units are pictures. Most relevant parts have been added or modified using Underline denoted, and some deleted portions are shown as strikethroughs. There may be some other changes that are editorial in nature and are therefore not highlighted. 6.1. Example 1 This embodiment is for the case where for solution item 1 and all its sub-items outlined in section 5 above, the video unit is a picture. 6.2. Example 2 This embodiment is for the case where for solution item 3 and all its sub-items outlined in section 5 above, the video unit is a picture. 6.3. Example 3 This embodiment is for the case where for solution item 5 and all its sub-items outlined in section 5 above, the video unit is a picture.

[0063] More details of embodiments of the present disclosure related to neural network post-filter activation will be described below. The embodiments of the present disclosure should be considered as examples to explain general concepts and should not be interpreted in a narrow manner. In addition, these embodiments can be applied individually or in combination in any way.

[0064] As used herein, the term "video unit" may refer to a color component, a sub-picture, a picture, a slice, a tile, a codec tree unit (CTU), a CTU row, a CTU group, a codec unit (CU), a prediction unit (PU), a transform unit (TU), a codec tree block (CTB), a codec 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 including multiple samples / pixels, etc. A video unit may be rectangular or non-rectangular. In addition, the terms "neural network post-processing filter" and "neural network post-filter" may be used interchangeably.

[0065] Figure 5 FIG. 5 is a flow chart of a method 500 for video processing according to some embodiments of the present disclosure. Figure 5 As shown, at 502, 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.

[0066] In some embodiments, the bitstream includes a first indication that a target neural network post-processing filter (NNPF) is allowed to be activated. The target NNPF is applied to multiple video units of the video. In other words, only one first indication can be used to activate the target NNPF to be applied to multiple video units, and the target NNPF maintains multiple video units. That is, the first indication can be used to enable the target NNPF to be applied to multiple video units, rather than just a single video unit. It should be noted that if necessary, the first indication can also be used to enable the target NNPF to be applied to a single video unit. As an example and not limitation, the first indication can be a syntax element nnpfa_persistence_flag. It should be understood that the first indication can also be a syntax element represented by any other suitable string. The scope of the present disclosure is not limited in this respect.

[0067] In view of the above, the first indication in the bitstream is allowed to activate the target NNPF to be applied to multiple video units. Compared with the traditional solution in which the activation indication is maintained for only a single video unit, the proposed method can advantageously reduce the number of indications required to transmit activation information through the signal, and thus the coding efficiency can be improved.

[0068] In some embodiments, multiple video units may be located in the same layer as the current video block, i.e., the current layer. In this case, the first indication specifies the maintenance of the target NNPF for the current layer. In one example, the multiple video units may include multiple consecutive video units in output order. In another example, the multiple video units may include multiple consecutive video units in decoding order. In yet another example, the multiple video units may include multiple video units with the same parameters (e.g., picture-level quantization parameters, picture types, temporal layer ids) in output order. In yet another example, the multiple video units may include samples of a set of pictures associated with the same color component. It should be understood that the above description is described for descriptive purposes only. The scope of the present disclosure is not limited in this respect.

[0069] In some embodiments, the bitstream may further include a second indication for indicating an identification number of the target NNPF. As an example and not limitation, the second indication may be a syntax element nnpfa_id. It should be understood that the first indication may also be a syntax element represented by any other suitable string, such as nnpfa_target_id. The scope of the present disclosure is not limited in this respect.

[0070] In some embodiments, the bitstream may further include a third indication for indicating the deactivation of the target NNPF. As an example and not limitation, the third indication may be a syntax element nnpfa_cancel_flag. It should be understood that the first indication may also be a syntax element represented by any other suitable string. The scope of the present disclosure is not limited in this respect.

[0071] In some embodiments, the first indication, the second indication and / or the third indication may be included in a Neural Network Post Filter Activation (NNPFA) Supplemental Enhancement Information (SEI) message in the bitstream.

[0072] In some embodiments, a third indication equal to a first value (e.g., 1, etc.) may be used to indicate that maintenance of a target NNPF established by a previous NNPFA SEI message having the same second indication as the current SEI message is canceled. As an example and not limitation, a syntax element nnpfa_cancel_flag equal to 1 indicates that maintenance of a target NNPF established by any previous NNPFA SEI message having the same syntax element nnpfa_target_id as the current SEI message is canceled, i.e., the target NNPF is no longer used unless the target NNPF is activated by another NNPFA SEI message having the same syntax element nnpfa_target_id as the current SEI message and a syntax element nnpfa_cancel_flag equal to 0.

[0073] Additionally, a third indication equal to a second value (eg, 0, etc.) may be used to indicate that the first indication follows the third indication in the bitstream.As an example and not limitation, a syntax element nnpfa_cancel_flag equal to 0 indicates that at least a syntax element nnpfa_persistence_flag follows it.

[0074] In some embodiments, a first indication equal to a third value (e.g., 0, etc.) may be used to indicate that the target NNPF is only used for post-processing filtering for the current video unit. As an example and not limitation, a syntax element nnpfa_persistence_flag equal to 0 specifies that the target NNPF may only be used for post-processing filtering for the current picture.

[0075] In addition, a first indication equal to a fourth value (e.g., 1, etc.) can be used to indicate that the target NNPF is used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in output order until one or more of the following three conditions are met.

[0076] First condition: another coded layer video sequence (CLVS) of the current layer starts, the other CLVS being different from the current CLVS associated with the current video unit. For example, a new CLVS of the current layer starts to be processed.

[0077] Second condition: the bitstream ends. For example, the processing of the video bitstream is completed, or the current video unit is the last video unit included in the bitstream.

[0078] Third condition: another video unit in the current layer associated with an NPNFA SEI message is output, the NPNFA SEI message has the same second indication as the current SEI message, and the other video unit is after the current video unit in the output order. In some embodiments, the other video is after the current video unit in the output order, and the target NNPF is not applied to the other video unit.

[0079] As an example and not limitation, the syntax element nnpfa_persistence_flag equal to 1 specifies that the target NNPF may be used for post-processing filtering for the current picture and all subsequent pictures of the current layer in output order until one or more of the following conditions are true: (1) a new CLVS for the current layer starts, (2) the bitstream ends, (3) a picture in the current layer associated with an NNPFA SEI message having the same syntax element nnpfa_target_id as the current SEI message is output, and the picture follows the current picture in output order. It should be noted that the target NNPF is not applied to this subsequent picture in the current layer associated with an NNPFA SEI message having the same syntax element nnpfa_target_id as the current SEI message.

[0080] In some alternative embodiments, a first indication equal to an eighth value (e.g., 1, etc.) may be used to indicate that the target NNPF may be used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in decoding order until one or more of the following conditions are met: another coded layer video sequence (CLVS) of the current layer begins, the other CLVS being different from the current CLVS associated with the current video unit; the bitstream ends; or another video unit in the current layer associated with an NNPFA SEI message may be decoded, the NNPFA SEI message having the same second indication as the current SEI message, the other video unit being after the current video unit in decoding order. In some embodiments, the target NNPF is not applied to the other video unit.

[0081] As an example and not limitation, the syntax element nnpfa_persistence_flag equal to 1 specifies that the target neural network post-processing filter can be used for post-processing filtering for the current picture and all subsequent pictures of the current layer in decoding order until one or more of the following conditions are true: (1) a new CLVS for the current layer starts, (2) the bitstream ends, (3) a picture in the current layer associated with an NNPFA SEI message is decoded, the NNPFA SEI message having the same syntax element nnpfa_id as the current SEI message and the syntax element nnpfa_cancel_flag equal to 1, the picture following the current picture in decoding order. It should be noted that the target neural network post-processing filter is not applied to this subsequent picture in the current layer associated with an NNPFA SEI message having the same syntax element nnpfa_id as the current SEI message and the syntax element nnpfa_cancel_flag equal to 1.

[0082] In some embodiments, the second indication may include a syntax element nnpfa_id. As an example and not limitation, the syntax element nnpfa_id specifies a target neural network post-processing filter specified by one or more neural network post-filter characteristics (NNPFC) SEI messages associated with the current picture and having nnpfc_id equal to nnfpa_id.

[0083] In some embodiments, the first indication may include a syntax element nnpfa_on_flag. In some embodiments, the first indication equal to a fifth value (e.g., 0, etc.) may be used to indicate that maintenance of the target NNPF is canceled. As an example and not limitation, the syntax element nnpfa_on_flag equal to 0 specifies that maintenance of the target neural network post-processing filter is canceled, i.e., the target neural network post-processing filter is no longer used unless the target neural network post-processing filter is activated by another NNPFA SEI message having a syntax element nnpfa_on_flag equal to 1 and a syntax element nnpfa_id identical to the current SEI message.

[0084] In some embodiments, a first indication equal to a sixth value (e.g., 1, etc.) may be used to indicate that the target NNPF may be used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in output order until one or more of the following conditions are met: (1) another CLVS of the current layer begins, the other CLVS being different from the current CLVS associated with the current video unit, (2) the end of the bitstream, or (3) another video unit in the current layer associated with an NNPFA SEI message is output, the NNPFA SEI message having a first indication equal to the fifth value and a second indication identical to the current SEI message, the other video unit being after the current video unit in output order. In some embodiments, the target NNPF may not be applied to the other video unit.

[0085] By way of example and not limitation, the syntax element nnpfa_on_flag being equal to 1 specifies that the target neural network post-processing filter may be used for post-processing filtering for the current video unit and all subsequent video units of the current layer in output order until one or more of the following conditions are true: (1) a new CLVS for the current layer begins, (2) the bitstream ends, (3) a video unit in the current layer associated with an NNPFA SEI message is output, the NNPFA SEI message having the syntax element nnpfa_on_flag being equal to 0 and the syntax element nnpfa_id being the same as the current SEI message, the video unit following the current video unit in output order. Note that the target neural network post-processing filter is not applied to this subsequent picture in the current layer associated with an NNPFA SEI message having the syntax element nnpfa_on_flag being equal to 0 and the syntax element nnpfa_id being the same as the current SEI message.

[0086] In some embodiments, a first indication equal to the seventh value (e.g., 1, etc.) may be used to indicate that the target NNPF may be used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in decoding order until one or more of the following conditions are met: (1) another CLVS of the current layer begins, the other CLVS being different from the current CLVS associated with the current video unit, (2) the end of the bitstream, or (3) another video unit in the current layer associated with an NNPFA SEI message may be decoded, the NNPFA SEI message having a first indication equal to the fifth value and a second indication identical to the current SEI message, the other video unit being subsequent to the current video unit in decoding order. In some embodiments, the target NNPF may not be applied to the other video unit.

[0087] By way of example and not limitation, the syntax element nnpfa_on_flag being equal to 1 specifies that the target neural network post-processing filter may be used for post-processing filtering for the current video unit and all subsequent video units of the current layer in decoding order until one or more of the following conditions are true: (1) a new CLVS for the current layer begins, (2) the bitstream ends, (3) a picture in the current layer associated with an NNPFA SEI message is decoded, the NNPFA SEI message having the syntax element nnpfa_on_flag being equal to 0 and the syntax element nnpfa_id being the same as the current SEI message, the picture following the current picture in decoding order. Note that the target neural network post-processing filter is not applied to this subsequent video unit in the current layer associated with an NNPFA SEI message having the syntax element nnpfa_on_flag being equal to 0 and the syntax element nnpfa_id being the same as the current SEI message.

[0088] In some embodiments, the first indication may include a first SEI message. For example, the first SEI message may be a neural network post filter deactivation (NNPFD) SEI message and may include a second indication. The second indication may be a syntax element nnpfd_id.

[0089] As an example and not limitation, the NNPFD SEI message may contain only the ue(v) codec syntax element nnpfd_id, where nnpfd_id specifies the target neural network post-processing filter, which is specified by one or more neural network post-processing filter characteristics (NNPFC) SEI messages related to the current picture and having nnpfc_id equal to nnfpd_id.

[0090] In some embodiments, multiple target NNPFs may be indicated in the first SEI message.In some alternative embodiments, multiple instances of the second indication may be indicated in the bitstream.

[0091] As an example and not limitation, instead of signaling one target neural network post-processing filter, multiple target neural network post-processing filters may be indicated in the NNPFD SEI message.Alternatively or additionally, multiple instances of the syntax element nnpfd_id may be signaled.

[0092] In some embodiments, the first SEI message deactivates the application of the target NNPF indicated by the second indication. As an example and not limitation, the NNPFD SEI message deactivates the possible use of the target neural network post-processing filter specified by the syntax element nnpfd_id. Once the target neural network post-processing filter is deactivated, the target neural network post-processing filter is no longer used unless the target neural network post-processing filter is reactivated by a subsequent NNPFA SEI message in decoding order, the syntax element nnpfa_id of the NNPFA SEI message being equal to the syntax element nnpfd_id of the current SEI message.

[0093] In some embodiments, the NPFFA SEI message activates application of a target NNPF for post-processing filtering of a plurality of video units, and the target NNPF may be indicated by a first syntax element. For example, the first syntax element may be a syntax element nnpfa_id.

[0094] As an example and not limitation, the NNPFA SEI message activates possible use of a target neural network post-processing filter specified by nnpfa_id for post-processing filtering of a set of pictures. The syntax element nnpfa_id is used to specify a target neural network post-processing filter specified by one or more neural network post-filter characteristics (NNPFC) SEI messages associated with the current picture and having a syntax element nnpfc_id equal to the syntax element nnfpa_id.

[0095] In some embodiments, the target NNPF may be used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in output order until one or more of the following conditions are met: (1) another CLVS of the current layer begins, the other CLVS being different from the current CLVS associated with the current video unit, (2) the bitstream ends, or (3) another video unit in the current layer associated with the first SEI message may be output, the first SEI message having a second indicated value equal to the value of the first syntax element, the other video unit following the current video in output order. In some embodiments, the target NNPF is not applied to the other video unit.

[0096] By way of example and not limitation, the target neural network post-processing filter may be used for post-processing filtering for the current picture and all subsequent pictures of the current layer in output order until one or more of the following conditions are true: (1) a new CLVS for the current layer begins, (2) the bitstream ends, (3) a picture in the current layer associated with a neural network post-filter deactivation (NNPFD) SEI message having a syntax element nnpfd_id equal to the syntax element nnpfa_id is output, the picture following the current picture in output order. It should be noted that the target neural network post-processing filter is not applied to this subsequent picture in the current layer associated with an NNPFD SEI message having a syntax element nnpfd_id equal to the syntax element nnpfa_id.

[0097] In some embodiments, the target NNPF may be used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in decoding order until one or more of the following conditions are met: another CLVS of the current layer begins, the other CLVS being different from the current CLVS associated with the current video unit; the bitstream ends; or another video unit in the current layer associated with the first SEI message may be decoded, the first SEI message having a second indicated value equal to the value of the first syntax element, the other video unit following the current video unit in decoding order. In some embodiments, the target NNPF is not applied to the other video unit.

[0098] By way of example and not limitation, the target neural network post-processing filter may be used for post-processing filtering for the current picture and all subsequent pictures of the current layer in decoding order until one or more of the following conditions are true: (1) a new CLVS for the current layer begins, (2) the bitstream ends, (3) a picture in the current layer associated with a neural network post-filter deactivation (NNPFD) SEI message having a syntax element nnpfd_id equal to the syntax element nnpfa_id is decoded, which picture follows the current picture in decoding order. It should be noted that the target neural network post-processing filter is not applied to this subsequent picture in the current layer associated with an NNPFD SEI message having a syntax element nnpfd_id equal to the syntax element nnpfa_id.

[0099] In some embodiments, information about how to interpret the activation message for the target NNPF may depend on the codec information of the current video unit, and the activation message may be included in the SEI message for the current video unit. As an example and not limitation, the codec information may include a slice type, a picture type, a quantization parameter (QP), information about whether the current video unit is losslessly encoded, and the like. In one example, the SEI message may be interpreted differently for I slices (I pictures) and P slices or B slices (pictures). In another example, the SEI message may be interpreted differently for video units with different QPs. In yet another example, the SEI message may be interpreted differently for losslessly encoded or lossily encoded video units.

[0100] In some embodiments, the number of multiple video units can be indicated in the bitstream. For example, the number of consecutive video units (e.g., pictures or a group of pictures with specific attributes) in output order to which the NN-based post-processing filter can be applied is signaled in the NNPFA SEI message. Alternatively, the number of consecutive video units in decoding order to which the NN-based post-processing filter can be applied is signaled in the NNPFA SEI message.

[0101] According to another embodiment 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 generated by a method performed by a device for video processing. In the method, a conversion between a current video unit of the video and the bitstream is performed. The bitstream includes a first indication that a target neural network post-processing filter (NNPF) is allowed to be activated, and the target NNPF is applied to multiple video units of the video.

[0102] According to some other embodiments of the present disclosure, a method for storing a bitstream of a video is provided. According to the method, a conversion between a current video unit of the video and a bitstream is performed. The bitstream includes a first indication that a target neural network post-processing filter (NNPF) is allowed to be activated, and the target NNPF is applied to multiple video units of the video. In addition, the bitstream is stored in a non-transitory computer-readable recording medium.

[0103] The exemplary embodiments of the present disclosure are described above with reference to a neural network post-processing filter. It should be understood that the concepts of the present disclosure can also be applied to any other suitable neural network-based operations, such as a neural network-based downsampling filter, a neural network-based upsampling filter, etc. The scope of the present disclosure is not limited in this regard.

[0104] Embodiments of the present disclosure may be described according to the following clauses, features of which may be combined in any reasonable way.

[0105] Item 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 includes a first indication that a target neural network post-processing filter (NNPF) is allowed to be activated, and the target NNPF is applied to multiple video units of the video.

[0106] Clause 2. The method of clause 1, wherein the bitstream further comprises a second indication of an identification number of the target NNPF.

[0107] Clause 3. A method according to any one of clauses 1 to 2, wherein the multiple video units are located at the same layer as the current video block, and the multiple video units include one of the following: multiple consecutive video units in output order, multiple consecutive video units in decoding order, or multiple video units with the same parameters in output order.

[0108] Clause 4. The method of any one of clauses 1 to 3, wherein the video unit is a picture or a slice.

[0109] Clause 5. A method according to any one of clauses 1 to 4, wherein the first indication is included in a Neural Network Post Filter Activation (NNPFA) Supplemental Enhancement Information (SEI) message in the bitstream.

[0110] Clause 6. A method according to any one of clauses 1 to 5, wherein the bitstream further comprises a third indication for indicating deactivation of the target NNPF.

[0111] Clause 7. The method of clause 6, wherein the third indication is included in a NNPFA SEI message in the bitstream.

[0112] Clause 8. A method according to any of clauses 6 to 7, wherein the first indication comprises a syntax element nnpfa_persistence_flag, or the third indication comprises a syntax element nnpfa_cancel_flag.

[0113] Clause 9. A method according to any of clauses 6 to 8, wherein the third indication equal to the first value is used to indicate that maintenance of the target NNPF established by a previous NNPFA SEI message having the same second indication as the current SEI message is cancelled.

[0114] Clause 10. The method of clause 9, wherein the first value is 1.

[0115] Clause 11. The method of any of clauses 9 to 10, wherein a third indication equal to the second value is used to indicate that the first indication follows the third indication in the bitstream.

[0116] Clause 12. The method of clause 11, wherein the second value is zero.

[0117] Clause 13. The method of any one of clauses 1 to 12, wherein the first indication equal to the third value is used to indicate that the target NNPF is used for post-processing filtering only for the current video unit.

[0118] Clause 14. The method of clause 13, wherein the third value is zero.

[0119] Clause 15. A method according to any one of clauses 13 to 14, wherein the first indication equal to the fourth value is used to indicate that the target NNPF is used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in output order until one or more of the following conditions are met: another coded layer video sequence (CLVS) of the current layer starts, the other CLVS is different from the current CLVS associated with the current video unit, the bitstream ends, or another video unit in the current layer associated with an NNPFA SEI message is output, the NNPFASEI message has the same second indication as the current SEI message, and the other video unit is after the current video unit in output order.

[0120] Clause 16. The method of clause 15, wherein the target NNPF is not applied to another video unit.

[0121] Clause 17. The method of any one of clauses 15 to 16, wherein the fourth value is 1.

[0122] Clause 18. A method according to any of clauses 2 to 17, wherein the second indication comprises a syntax element nnpfa_id.

[0123] Clause 19. A method according to any of clauses 1 to 5 and 18, wherein the first indication comprises a syntax element nnpfa_on_flag.

[0124] Clause 20. The method of any one of clauses 1 to 5 and 18 to 19, wherein the first indication equal to the fifth value is used to indicate that maintenance of the target NNPF is cancelled.

[0125] Clause 21. A method according to clause 20, wherein the first indication equal to the sixth value is used to indicate that the target NNPF is used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in output order until one or more of the following conditions are met: another CLVS of the current layer starts, the other CLVS is different from the current CLVS associated with the current video unit, the bitstream ends, or another video unit in the current layer associated with an NNPFASEI message is output, the NNPFA SEI message has a first indication equal to the fifth value and a second indication that is the same as the current SEI message, and the other video unit is after the current video unit in output order.

[0126] Clause 22. A method according to clause 20, wherein the first indication equal to the seventh value is used to indicate that the target NNPF is used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in decoding order until one or more of the following conditions are met: another CLVS of the current layer starts, the other CLVS is different from the current CLVS associated with the current video unit, the bitstream ends, or another video unit in the current layer associated with an NNPFASEI message is decoded, the NNPFASEI SEI message having a first indication equal to the fifth value and a second indication that is the same as the current SEI message, and the other video unit is after the current video unit in decoding order.

[0127] Clause 23. The method of any of clauses 21 to 22, wherein the target NNPF is not applied to another video unit.

[0128] Clause 24. A method as described in any of clauses 1 to 4, wherein the first indication comprises a first SEI message.

[0129] Clause 25. The method of clause 24, wherein the first SEI message is a neural network post filter deactivation (NNPFD) SEI message and includes the second indication.

[0130] Clause 26. The method of clause 25, wherein the second indication is a syntax element nnpfd_id.

[0131] Clause 27. A method as described in any of clauses 24 to 26, wherein a plurality of target NNPFs are indicated in the first SEI message.

[0132] Clause 28. The method of any of clauses 24 to 27, wherein multiple instances of the second indication are indicated in the bitstream.

[0133] Clause 29. A method according to any one of clauses 24 to 28, wherein the first SEI message deactivates an application of a target NNPF indicated by the second indication.

[0134] Clause 30. The method of any of clauses 24 to 28, wherein the NNPFA SEI message activates application of a target NNPF for post-processing filtering of the plurality of video units, the target NNPF being indicated by the first syntax element.

[0135] Clause 31. The method of clause 30, wherein the first syntax element is the syntax element nnpfa_id.

[0136] Clause 32. A method according to any one of clauses 30 to 31, wherein the target NNPF is used for post-processing filtering for a current video unit and all subsequent video units of the current layer associated with the current video unit in output order until one or more of the following conditions is met: another CLVS of the current layer starts, the other CLVS is different from the current CLVS associated with the current video unit, the bitstream ends, or another video unit in the current layer associated with the first SEI message is output, the first SEI message has a second indicated value that is equal to the value of the first syntax element, and the other video unit follows the current video unit in output order.

[0137] Clause 33. A method according to any one of clauses 30 to 31, wherein the target NNPF is used for post-processing filtering for a current video unit and all subsequent video units of the current layer associated with the current video unit in decoding order until one or more of the following conditions is met: another CLVS of the current layer starts, the other CLVS is different from the current CLVS associated with the current video unit, the bitstream ends, or another video unit in the current layer associated with a first SEI message is decoded, the first SEI message has a second indicated value that is equal to the value of the first syntax element, and the other video unit follows the current video unit in decoding order.

[0138] Clause 34. A method according to any one of clauses 13 to 14, wherein the first indication equal to the eighth value is used to indicate that the target NNPF is used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in decoding order until one or more of the following conditions are met: another coded layer video sequence (CLVS) of the current layer starts, the other CLVS is different from the current CLVS associated with the current video unit, the bitstream ends, or another video unit in the current layer associated with an NNPFA SEI message is decoded, the NNPFA SEI message has the same second indication as the current SEI message, and the other video unit is after the current video unit in decoding order.

[0139] Clause 35. The method of any of clauses 32 to 35, wherein the target NNPF is not applied to another video unit.

[0140] Clause 36. A method according to any one of clauses 1 to 35, wherein information about how to interpret an activation message for a target NNPF depends on codec information of a current video unit, the activation message being included in a SEI message for the current video unit.

[0141] Clause 37. The method of clause 36, wherein the codec information comprises at least one of: a slice type, a picture type, a quantization parameter (QP), or information on whether the current video unit is losslessly encoded.

[0142] Clause 38. The method of any one of clauses 1 to 38, wherein the number of the plurality of video units is indicated in the bitstream.

[0143] Clause 39. The method of any one of clauses 1 to 38, wherein converting comprises encoding the current video unit into a bitstream.

[0144] Clause 40. The method of any one of clauses 1 to 38, wherein converting comprises decoding the current video unit from a bitstream.

[0145] Clause 41. An apparatus for video processing, comprising a processor and a non-transitory memory having instructions, wherein the instructions, when executed by the processor, cause the processor to perform a method according to any one of clauses 1 to 40.

[0146] Clause 42. A non-transitory computer-readable storage medium storing instructions that cause a processor to perform a method according to any one of clauses 1 to 40.

[0147] Item 43. A non-transitory computer-readable recording medium storing a bitstream of a video, the bitstream being generated by a method executed by a video processing device, wherein the method comprises: performing a conversion between a current video unit of the video and the bitstream, wherein the bitstream includes a first indication that a target neural network post-processing filter (NNPF) is allowed to be activated, and the target NNPF is applied to multiple video units of the video.

[0148] Item 44. A method for storing a bitstream of a video, comprising: performing a conversion between a current video unit of the video and a bitstream, wherein the bitstream includes a first indication that a target neural network post-processing filter (NNPF) is allowed to be activated, the target NNPF being applied to multiple video units of the video; and storing the bitstream in a non-transitory computer-readable recording medium. Example Device

[0149] Figure 6 A block diagram of a computing device 600 in which various embodiments of the present disclosure may be implemented is shown. The computing device 600 may be implemented as a source device 110 (or video encoder 114 or 200) or a destination device 120 (or video decoder 124 or 300), or may be included in a source device 110 (or video encoder 114 or 200) or a destination device 120 (or video decoder 124 or 300).

[0150] It should be understood that Figure 6 The computing device 600 shown in FIG. 6 is for illustrative purposes only and is not intended to in any way imply any limitation on the functionality and scope of the embodiments of the present disclosure.

[0151] like Figure 6 As shown, computing device 600 comprises a general computing device 600. Computing device 600 may include at least one or more processors or processing units 610, memory 620, storage unit 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660.

[0152] In some embodiments, the computing device 600 can be implemented as any user terminal or server terminal with computing power. The server terminal can be a server, a large computing device, etc. provided by a service provider. The user terminal can be, for example, any type of mobile terminal, fixed terminal or portable terminal, including a mobile phone, a station, a unit, a device, a multimedia computer, a multimedia tablet computer, an Internet node, a communicator, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an electronic book device, a gaming device, or any combination thereof, including the accessories and peripherals of these devices, or any combination thereof. It is conceivable that the computing device 600 can support any type of interface to the user (such as a "wearable" circuit device, etc.).

[0153] The processing unit 610 may be a physical processor or a virtual processor and may implement various processes based on a program stored in the memory 620. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to increase 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.

[0154] The computing device 600 typically includes various computer storage media. Such media can be any media accessible by the computing device 600, including but not limited to volatile media and non-volatile media, or removable media and non-removable media. The memory 620 can be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (such as a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM) or flash memory) or any combination thereof. The storage unit 630 can be any removable or non-removable medium, and can include machine-readable media, such as a memory, a flash drive, a disk, or other media that can be used to store information and / or data and can be accessed in the computing device 600.

[0155] The computing device 600 may also include additional removable / non-removable storage media, volatile / non-volatile storage media. Figure 6 Although not shown in the figure, a disk drive for reading from and / or writing to a removable nonvolatile disk and an optical drive for reading from and / or writing to a removable nonvolatile optical disk may be provided. In this case, each drive may be connected to the bus (not shown) via one or more data medium interfaces.

[0156] The communication unit 640 communicates with another computing device via a 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, which can communicate via a communication connection. Therefore, the computing device 600 can operate in a networked environment using logical connections to one or more other servers, networked personal computers (PCs), or other general network nodes.

[0157] The input device 650 may be one or more of various input devices, such as a mouse, keyboard, trackball, voice input device, etc. The output device 660 may be one or more of various output devices, such as a display, a speaker, a printer, etc. With the aid of the communication unit 640, the computing device 600 may also communicate with one or more external devices (not shown), such as storage devices and display devices, and the computing device 600 may also communicate with one or more devices that enable a user to interact with the computing device 600, or, if necessary, the computing device 600 may also communicate with any device (e.g., a network card, a modem, etc.) that enables the computing device 600 to communicate with one or more other computing devices. Such communication may be performed via an input / output (I / O) interface (not shown).

[0158] In some embodiments, some or all components of the computing device 600 may also be arranged in a cloud computing architecture rather than being integrated in a single device. In a cloud computing architecture, components may be provided remotely and work together to implement the functions described in the present disclosure. In some embodiments, cloud computing provides computing, software, data access and storage services, which will not require the end user to know the physical location or configuration of the system or hardware that provides these services. In various embodiments, cloud computing provides services via a wide area network (such as the Internet) using a suitable protocol. For example, a cloud computing provider provides an application via a wide area network, which can be accessed through a web browser or any other computing component. The software or components of the cloud computing architecture and the corresponding data may be stored on a server at a remote location. The computing resources in a cloud computing environment may be merged or distributed at the location of a remote data center. Cloud computing infrastructure can provide services through a shared data center, although they appear as a single access point to the user. Therefore, the cloud computing architecture may be used to provide the components and functions described herein from a service provider at a remote location. Alternatively, the components and functions described herein may be provided by a conventional server, or may be installed on a client device directly or otherwise.

[0159] In an embodiment of the present disclosure, the computing device 600 may be used to implement video encoding / decoding. The memory 620 may include one or more video encoding / decoding modules 625 having one or more program instructions. These modules are accessible and executable by the processing unit 610 to perform the functions of the various embodiments described herein.

[0160] In an example embodiment performing video encoding, input device 650 may receive video data as input 670 to be encoded. The video data may be processed, for example, by video codec module 625 to generate an encoded bitstream. The encoded bitstream may be provided as output 680 via output device 660.

[0161] In an example embodiment performing video decoding, input device 650 may receive an encoded bitstream as input 670. The encoded bitstream may be processed, for example, by video codec module 625 to generate decoded video data. The decoded video data may be provided as output 680 via output device 660.

[0162] Although the present disclosure has been specifically shown and described with reference to the preferred embodiments of the present disclosure, it will be appreciated by those skilled in the art that various changes may be made in form and detail without departing from the spirit and scope of the present application as defined by the appended claims. These modifications are intended to be encompassed by the scope of the present application. Therefore, the foregoing description of the embodiments of the present application is not intended to be limiting.

Claims

1. A method for video processing, comprising: A conversion is performed between a current video unit of a video and a bitstream of the video, wherein the bitstream includes a first indication that a target neural network post-processing filter (NNPF) is enabled to be activated, and the target NNPF is applied to multiple video units of the video. 2 . The method according to claim 1 , wherein the bitstream further comprises a second indication for indicating an identification number of the target NNPF.

3. The method according to any one of claims 1 to 2, wherein the plurality of video units are located in the same layer as the current video block, and the plurality of video units include one of the following: Multiple consecutive video units in output order, Multiple consecutive video units in decoding order, or A plurality of video units having the same parameters in the output order. The method according to claim 1 , wherein the video unit is a picture or a slice.

5. The method according to any one of claims 1 to 4, wherein the first indication is included in a Neural Network Post Filter Activation (NNPFA) Supplemental Enhancement Information (SEI) message in the bitstream. 6 . The method according to claim 1 , wherein the bitstream further comprises a third indication for indicating deactivation of the target NNPF. 7 . The method of claim 6 , wherein the third indication is included in an NNPFA SEI message in the bitstream.

8. The method according to any one of claims 6 to 7, wherein the first indication comprises a syntax element nnpfa_persistence_flag, or the third indication comprises a syntax element nnpfa_cancel_flag.

9. The method according to any one of claims 6 to 8, wherein the third indication equal to the first value is used to indicate that maintenance of the target NNPF established by a previous NNPFA SEI message having the same second indication as that of a current SEI message is cancelled. The method of claim 9 , wherein the first value is 1.

11. The method according to any one of claims 9 to 10, wherein the third indication equal to the second value is used to indicate that the first indication follows the third indication in the bitstream. The method according to claim 11 , wherein the second value is 0.

13. The method according to any one of claims 1 to 12, wherein the first indication equal to a third value is used to indicate that the target NNPF is only used for post-processing filtering for the current video unit. The method according to claim 13 , wherein the third value is 0.

15. The method of any one of claims 13 to 14, wherein the first indication equal to a fourth value is used to indicate that the target NNPF is used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in output order until one or more of the following conditions are met: another coded layer video sequence (CLVS) of the current layer, the another CLVS being different from the current CLVS associated with the current video unit, The bitstream ends, or Another video unit in the current layer associated with an NNPFA SEI message is output, the NNPFA SEI message having the same second indication as the current SEI message, the another video unit being subsequent to the current video unit in the output order. The method of claim 15 , wherein the target NNPF is not applied to the another video unit.

17. The method according to any one of claims 15 to 16, wherein the fourth value is 1.

18. The method according to any one of claims 2 to 17, wherein the second indication comprises a syntax element nnpfa_id.

19. The method according to any one of claims 1 to 5 and 18, wherein the first indication comprises a syntax element nnpfa_on_flag.

20. The method according to any one of claims 1 to 5 and 18 to 19, wherein the first indication equal to a fifth value is used to indicate that the maintenance of the target NNPF is cancelled.

21. The method of claim 20, wherein the first indication equal to a sixth value is used to indicate that the target NNPF is used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in output order until one or more of the following conditions are met: another CLVS of the current layer, the other CLVS being different from the current CLVS associated with the current video unit, The bitstream ends, or Another video unit in the current layer associated with an NNPFA SEI message having the first indication equal to the fifth value and the second indication identical to the current SEI message is output, the another video unit following the current video unit in the output order.

22. The method of claim 20, wherein the first indication equal to a seventh value is used to indicate that the target NNPF is used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in decoding order until one or more of the following conditions are met: another CLVS of the current layer, the other CLVS being different from the current CLVS associated with the current video unit, The bitstream ends, or Another video unit in the current layer associated with an NNPFA SEI message having the first indication equal to the fifth value and the second indication identical to the current SEI message is decoded, the another video unit being subsequent to the current video unit in the decoding order.

23. The method according to any one of claims 21 to 22, wherein the target NNPF is not applied to the another video unit.

24. The method according to any one of claims 1 to 4, wherein the first indication comprises a first SEI message.

25. The method of claim 24, wherein the first SEI message is a neural network post filter deactivation (NNPFD) SEI message and includes the second indication.

26. The method of claim 25, wherein the second indication is a syntax element nnpfd_id.

27. The method according to any one of claims 24 to 26, wherein a plurality of target NNPFs are indicated in the first SEI message.

28. A method according to any one of claims 24 to 27, wherein multiple instances of the second indication are indicated in the bitstream.

29. The method according to any one of claims 24 to 28, wherein the first SEI message deactivates the application of the target NNPF indicated by the second indication.

30. The method of any one of claims 24 to 28, wherein an NNPFA SEI message activates application of the target NNPF for post-processing filtering of the plurality of video units, the target NNPF being indicated by a first syntax element.

31. The method of claim 30, wherein the first syntax element is a syntax element nnpfa_id.

32. The method of any one of claims 30 to 31, wherein the target NNPF is used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in output order until one or more of the following conditions are met: another CLVS of the current layer, the other CLVS being different from the current CLVS associated with the current video unit, The bitstream ends, or Another video unit in the current layer associated with the first SEI message is output, the first SEI message having a value of the second indication equal to a value of the first syntax element, the other video unit following the current video unit in the output order.

33. The method of any one of claims 30 to 31, wherein the target NNPF is used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in decoding order until one or more of the following conditions are met: another CLVS of the current layer, the other CLVS being different from the current CLVS associated with the current video unit, The bitstream ends, or Another video unit in the current layer associated with the first SEI message is decoded, the first SEI message having a value of the second indication equal to a value of the first syntax element, the other video unit following the current video unit in the decoding order.

34. The method of any one of claims 13 to 14, wherein the first indication equal to an eighth value is used to indicate that the target NNPF is used for post-processing filtering for the current video unit and all subsequent video units of the current layer associated with the current video unit in decoding order until one or more of the following conditions are met: another coded layer video sequence (CLVS) of the current layer, the another CLVS being different from the current CLVS associated with the current video unit, The bitstream ends, or Another video unit in the current layer associated with an NNPFA SEI message is decoded, the NNPFA SEI message having the same second indication as the current SEI message, the another video unit being subsequent to the current video unit in the decoding order.

35. The method of any one of claims 32 to 35, wherein the target NNPF is not applied to the another video unit.

36. A method according to any one of claims 1 to 35, wherein information about how to interpret an activation message for the target NNPF depends on codec information of the current video unit, and the activation message is included in a SEI message for the current video unit.

37. The method according to claim 36, wherein the codec information comprises at least one of the following: Strip type, Image type, Quantization Parameter (QP), or Information about whether the current video unit is losslessly encoded.

38. The method of any one of claims 1 to 38, wherein the number of the plurality of video units is indicated in the bitstream.

39. The method of any one of claims 1 to 38, wherein the converting comprises encoding the current video unit into the bitstream.

40. The method of any one of claims 1 to 38, wherein the converting comprises decoding the current video unit from the bitstream.

41. An apparatus for video processing, comprising a processor and a non-transitory memory having instructions, wherein the instructions, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 40.

42. A non-transitory computer-readable storage medium storing instructions, the instructions causing a processor to execute the method according to any one of claims 1 to 40.

43. A non-transitory computer-readable recording medium storing a bit stream of a video, the bit stream being generated by a method performed by a video processing device, wherein the method comprises: A conversion is performed between a current video unit of the video and the bitstream, wherein the bitstream includes a first indication that activation of a target neural network post-processing filter (NNPF) is allowed, the target NNPF being applied to multiple video units of the video.

44. 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 includes a first indication that activation of a target neural network post-processing filter (NNPF) is enabled, the target NNPF being applied to a plurality of video units of the video; as well as The bit stream is stored in a non-transitory computer-readable recording medium.

Images