Method, apparatus, and medium for visual data processing

Abstract

Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: performing a conversion between visual data and a codestream of the visual data with a neural network (NN)-based model, wherein the codestream comprises a first indication indicating a stream profile to which the codestream conforms.

Description

METHOD, APPARATUS, AND MEDIUM FOR VISUAL DATA PROCESSINGFIELDS

[0001] Embodiments of the present disclosure relates generally to visual data processing techniques, and more particularly, to neural network-based visual data coding.BACKGROUND

[0002] The past decade has witnessed the rapid development of deep learning in a variety of areas, especially in computer vision and image processing. Neural network was invented originally with the interdisciplinary research of neuroscience and mathematics. It has shown strong capabilities in the context of non-linear transform and classification. Neural networkbased image / video compression technology has gained significant progress during the past half decade. It is reported that the latest neural network-based image compression algorithm achieves comparable rate -distortion (R-D) performance with Versatile Video Coding (VVC). With the performance of neural image compression continually being improved, neural network-based video compression has become an actively developing research area. However, coding flexibility of neural network-based image / video coding is generally expected to be further improved.SUMMARY

[0003] Embodiments of the present disclosure provide a solution for visual data processing.

[0004] In a first aspect, a method for visual data processing is proposed. The method comprises: performing a conversion between visual data and a codestream of the visual data with a neural network (NN)-based model, wherein the codestream comprises a first indication indicating a stream profile to which the codestream conforms.

[0005] Based on the method in accordance with the first aspect of the present disclosure, the codestream comprises a first indication indicating a stream profile to which the codestream conforms. Compared with the conventional solution lacking such an indication, the proposed method can provide a mechanism for signaling of stream profile information, and thus can better support the application of different stream profiles. Thereby, the coding flexibility can be improved.

[0006] In a second aspect, an apparatus for visual data processing is proposed. The apparatus comprises a processor and a non-transitory memory with instructions thereon. The instructions upon execution by the processor, cause the processor to perform a method in accordance with the first aspect of the present disclosure.

[0007] In a third aspect, a non-transitory computer-readable storage medium is proposed. The non-transitory computer-readable storage medium stores instructions that cause a processor to perform a method in accordance with the first aspect of the present disclosure.

[0008] In a fourth aspect, another non-transitory computer-readable recording medium is proposed. The non-transitory computer-readable recording medium stores a codestream of visual data which is generated by a method performed by an apparatus for visual data processing. The method comprises: performing a conversion between the visual data and the codestream with a neural network (NN)-based model, wherein the codestream comprises a first indication indicating a stream profile to which the codestream conforms.

[0009] In a fifth aspect, a method for storing a codestream of visual data is proposed. The method comprises: performing a conversion between the visual data and the codestream with a neural network (NN)-based model; and storing the codestream in a non-transitory computer-readable recording medium, wherein the codestream comprises a first indication indicating a stream profile to which the codestream conforms.

[0010] 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

[0011] Through the following detailed description with reference to the accompanying drawings, the above and other objectives, features, and advantages of example embodiments of the present disclosure will become more apparent. In the example embodiments of the present disclosure, the same reference numerals usually refer to the same components.

[0012] Fig. 1A illustrates a block diagram that illustrates an example visual data coding system, in accordance with some embodiments of the present disclosure;

[0013] Fig. IB is a schematic diagram illustrating an example transform coding scheme;

[0014] Fig. 2 illustrates example latent representations of an image;

[0015] Fig. 3 is a schematic diagram illustrating an example autoencoder implementing a hyperprior model;

[0016] Fig. 4 is a schematic diagram illustrating an example combined model configured to jointly optimize a context model along with a hyperprior and the autoencoder;

[0017] Fig. 5 illustrates an example encoding process;

[0018] Fig. 6 illustrates an example decoding process;

[0019] Fig. 7 illustrates an example decoding process according to some embodiments of thepresent disclosure;

[0020] Fig. 8 illustrates a flowchart of a method for visual data processing in accordance with embodiments of the present disclosure; and

[0021] Fig. 9 illustrates a block diagram of a computing device in which various embodiments of the present disclosure can be implemented.

[0022] Throughout the drawings, the same or similar reference numerals usually refer to the same or similar elements.DETAILED DESCRIPTION

[0023] Principle of the present disclosure will now be described with reference to some embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. The disclosure described herein can be implemented in various manners other than the ones described below.

[0024] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

[0025] References in the present disclosure to “one embodiment,” “an embodiment,” “an example embodiment,” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an example embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

[0026] It shall be understood that although the terms “first” and “second” etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0027] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the contextclearly indicates otherwise. It will be further understood that the terms “comprises”, “comprising”, “has”, “having”, “includes” and / or “including”, when used herein, specify the presence of stated features, elements, and / or components etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.Example Environment

[0028] Fig. 1A is a block diagram that illustrates an example visual data coding system 100 that may utilize the techniques of this disclosure. As shown, the visual data coding system 100 may include a source device 110 and a destination device 120. The source device 110 can be also referred to as a visual data encoding device, and the destination device 120 can be also referred to as a visual data decoding device. In operation, the source device 110 can be configured to generate encoded visual data and the destination device 120 can be configured to decode the encoded visual data generated by the source device 110. The source device 110 may include a visual data source 112, a visual data encoder 114, and an input / output (I / O) interface 116.

[0029] The visual data source 112 may include a source such as a visual data capture device. Examples of the visual data capture device include, but are not limited to, an interface to receive visual data from a visual data provider, a computer graphics system for generating visual data, and / or a combination thereof.

[0030] The visual data may comprise one or more pictures of a video or one or more images. The visual data encoder 114 encodes the visual data from the visual data source 112 to generate a bitstream. The bitstream may include a sequence of bits that form a coded representation of the visual data. The bitstream may include coded pictures and associated visual data. The coded picture is a coded representation of a picture. The associated visual data may include sequence parameter sets, picture parameter sets, and other syntax structures. The I / O interface 116 may include a modulator / demodulator and / or a transmitter. The encoded visual data may be transmitted directly to destination device 120 via the I / O interface 116 through the network 130A. The encoded visual data may also be stored onto a storage medium / server 130B for access by destination device 120.

[0031] The destination device 120 may include an I / O interface 126, a visual data decoder 124, and a display device 122. The I / O interface 126 may include a receiver and / or a modem. The I / O interface 126 may acquire encoded visual data from the source device 110 or the storage medium / server 130B. The visual data decoder 124 may decode the encoded visual data. The display device 122 may display the decoded visual data to a user. The displaydevice 122 may be integrated with the destination device 120, or may be external to the destination device 120 which is configured to interface with an external display device.

[0032] The visual data encoder 114 and the visual data decoder 124 may operate according to a visual data coding standard, such as video coding standard or still picture coding standard and other current and / or further standards.

[0033] Some exemplary embodiments of the present disclosure will be described in detailed hereinafter. It should be understood that section headings are used in the present document to facilitate ease of understanding and do not limit the embodiments disclosed in a section to only that section. Furthermore, while certain embodiments are described with reference to Versatile Video Coding or other specific visual data codecs, the disclosed techniques are applicable to other coding technologies also. Furthermore, while some embodiments describe coding steps in detail, it will be understood that corresponding steps decoding that undo the coding will be implemented by a decoder. Furthermore, the term visual data processing encompasses visual data coding or compression, visual data decoding or decompression and visual data transcoding in which visual data are represented from one compressed format into another compressed format or at a different compressed bitrate.1. Brief SummaryThis disclosure is related to neural network (NN)-based image and video coding. Specifically, it is related to signalling of high-level information in neural network (NN)-based image or video bitstreams, e.g., an JPEG Al codestream. Such high-level information includes tools header information, bit depth information, and profile and level information. The ideas may be applied individually or in various combinations, for image and / or video coding methods and specifications.2. IntroductionThe past decade has witnessed the rapid development of deep learning in a variety of areas, especially in computer vision and image processing. Inspired from the great success of deep learning technology to computer vision areas, many researchers have shifted their attention from conventional image / video compression techniques to neural image / video compression technologies. Neural network was invented originally with the interdisciplinary research of neuroscience and mathematics. It has shown strong capabilities in the context of non-linear transform and classification. Neural network-based image / video compression technology has gained significant progress during the past half decade. It is reported that the latest neural networkbased image compression algorithm achieves comparable R-D performance with Versatile Video Coding (VVC), the latest video coding standard developed by Joint Video Experts Team (JVET) with experts from MPEG and VCEG. With the performance of neural image compressioncontinually being improved, neural network-based video compression has become an actively developing research area. However, neural network-based video coding still remains in its infancy due to the inherent difficulty of the problem.2.1. Image / video compressionImage / video compression (also referred to as image / video coding) usually refers to the computing technology that compresses image / video into binary code to facilitate storage and transmission. The binary codes may or may not support losslessly reconstructing the original image / video, termed lossless compression and lossy compression. Most of the efforts are devoted to lossy compression since lossless reconstruction is not necessary in most scenarios. Usually the performance of image / video compression algorithms is evaluated from two aspects, i.e. compression ratio and reconstruction quality. Compression ratio is directly related to the number of binary codes, the less the better; Reconstruction quality is measured by comparing the reconstructed image / video with the original image / video, the higher the better.Image / video compression techniques can be divided into two branches, the classical video coding methods and the neural-network-based video compression methods. Classical video coding schemes adopt transform-based solutions, in which researchers have exploited statistical dependency in the latent variables (e.g., DCT or wavelet coefficients) by carefully handengineering entropy codes modeling the dependencies in the quantized regime. Neural networkbased video compression is in two flavors, neural network-based coding tools and end-to-end neural network-based video compression. The former is embedded into existing classical video codecs as coding tools and only serves as part of the framework, while the latter is a separate framework developed based on neural networks without depending on classical video codecs.In the last three decades, a series of classical video coding standards have been developed to accommodate the increasing visual content. The international standardization organizations ISO / IEC has two expert groups namely Joint Photographic Experts Group (JPEG) and Moving Picture Experts Group (MPEG), and ITU-T also has its own Video Coding Experts Group (VCEG) which is for standardization of image / video coding technology. The influential video coding standards published by these organizations include JPEG, JPEG 2000, H.262, H.264 / AVC and H.265 / HEVC. After H.265 / HEVC, the Joint Video Experts Team (JVET) formed by MPEG and VCEG has been working on a new video coding standard Versatile Video Coding (VVC). The first version of VVC was released in July 2020. An average of 50% bitrate reduction is reported by VVC under the same visual quality compared with HEVC.Neural network-based image / video compression is not a new invention since there were a number of researchers working on neural network-based image coding. But the network architectures wererelatively shallow, and the performance was not satisfactory. Benefit from the abundance of data and the support of powerful computing resources, neural network-based methods are better exploited in a variety of applications. At present, neural network-based image / video compression has shown promising improvements, confirmed its feasibility. Nevertheless, this technology is still far from mature and a lot of challenges need to be addressed.2.2. Neural networksNeural networks, also known as artificial neural networks (ANN), are the computational models used in machine learning technology which are usually composed of multiple processing layers and each layer is composed of multiple simple but non-linear basic computational units. One benefit of such deep networks is believed to be the capacity for processing data with multiple levels of abstraction and converting data into different kinds of representations. Note that these representations are not manually designed; instead, the deep network including the processing layers is learned from massive data using a general machine learning procedure. Deep learning eliminates the necessity of handcrafted representations, and thus is regarded useful especially for processing natively unstructured data, such as acoustic and visual signal, whilst processing such data has been a longstanding difficulty in the artificial intelligence field.2.3. Neural networks for image and video compressionExisting neural networks for image compression methods can be classified in two categories, i.e., pixel probability modeling and auto-encoder. The former one belongs to the predictive coding strategy, while the latter one is the transform-based solution. Sometimes, these two methods are combined together in literature.Similar to conventional video coding technologies, neural image compression serves as the foundation of intra compression in neural network-based video compression, thus development of neural network-based video compression technology comes later than neural network-based image compression but needs far more efforts to solve the challenges due to its complexity. Starting from 2017, a few researchers have been working on neural network-based video compression schemes. Compared with image compression, video compression needs efficient methods to remove interpicture redundancy. Inter-picture prediction is then a crucial step in these works. Motion estimation and compensation is widely adopted but is not implemented by trained neural networks until recently.Studies on neural network-based video compression can be divided into two categories according to the targeted scenarios: random access and the low-latency. In random access case, it requires the decoding can be started from any point of the sequence, typically divides the entire sequence into multiple individual segments and each segment can be decoded independently. In low-latencycase, it aims at reducing decoding time thereby usually merely temporally previous frames can be used as reference frames to decode subsequent frames.Pixel probability modelingAccording to Shannon’s information theory, the optimal method for lossless coding can reach the minimal coding rate — log2p(x) where p(x) is the probability of symbol x. A number of lossless coding methods were developed in literature and among them arithmetic coding is believed to be among the optimal ones. Given a probability distribution p(x), arithmetic coding ensures that the coding rate to be as close as possible to its theoretical limit — log2p(x) without considering the rounding error. Therefore, the remaining problem is to how to determine the probability, which is however very challenging for natural image / video due to the curse of dimensionality.Following the predictive coding strategy, one way to model p(x) is to predict pixel probabilities one by one in a raster scan order based on previous observations, where x is an image. p(x) = p(x1)p(x2|x1) ... pCx x ... , xi-1) ... p(x7nxn|x17...^ x^.i) (1) where m and n are the height and width of the image, respectively. The previous observation is also known as the context of the current pixel. When the image is large, it can be difficult to estimate the conditional probability, thereby a simplified method is to limit the range of its context. p(x) = p(x1)p(x2|x1) ...pCxdXj.fc, ... , xi-1) ... p(xmxn|xmxn-k, .... x^- (2) where k is a pre-defined constant controlling the range of the context.It should be noted that the condition may also take the sample values of other color components into consideration. For example, when coding the RGB color component, R sample is dependent on previously coded pixels (including R / G / B samples), the current G sample may be coded according to previously coded pixels and the current R sample, while for coding the current B sample, the previously coded pixels and the current R and G samples may also be taken into consideration.Neural networks were originally introduced for computer vision tasks and have been proven to be effective in regression and classification problems. Therefore, it has been proposed using neural networks to estimate the probability of p(x ) given its context xltx2, ... , xi-1.Most of the methods directly model the probability distribution in the pixel domain. Some researchers also attempt to model the probability distribution as a conditional one upon explicit or latent representations. That being said, it may be estimated thatwhere h is the additional condition and p(x) = p( )p(x| ), meaning the modeling is split into an unconditional one and a conditional one. The additional condition can be image label information or high-level representations.Auto-encoderAuto-encoder originates from the well-known work proposed by Hinton and Salakhutdinov. The method is trained for dimensionality reduction and consists of two parts: encoding and decoding. The encoding part converts the high-dimension input signal to low-dimension representations, typically with reduced spatial size but a greater number of channels. The decoding part attempts to recover the high-dimension input from the low-dimension representation. Auto-encoder enables automated learning of representations and eliminates the need of hand-crafted features, which is also believed to be one of the most important advantages of neural networks.Fig. IB illustrates a typical transform coding scheme. The original image x is transformed by the analysis network gato achieve the latent representation y. The latent representation y is quantized and compressed into bits. The number of bits R is used to measure the coding rate. The quantized latent representation y is then inversely transformed by a synthesis network gsto obtain the reconstructed image x. The distortion is calculated in a perceptual space by transforming x and x with the function gp.It is intuitive to apply auto-encoder network to lossy image compression. It is only needed to encode the learned latent representation from the well-trained neural networks. However, it is not trivial to adapt auto-encoder to image compression since the original auto-encoder is not optimized for compression thereby not efficient by directly using a trained auto-encoder. In addition, there exist other major challenges: First, the low-dimension representation should be quantized before being encoded, but the quantization is not differentiable, which is required in backpropagation while training the neural networks. Second, the objective under compression scenario is different since both the distortion and the rate need to be take into consideration. Estimating the rate is challenging. Third, a practical image coding scheme needs to support variable rate, scalability, encoding / decoding speed, interoperability. In response to these challenges, a number of researchers have been actively contributing to this area.The prototype auto-encoder for image compression is in Fig. IB, which can be regarded as a transform coding strategy. The original image x is transformed with the analysis network y = ga(x), where y is the latent representation which will be quantized and coded. The synthesis network will inversely transform the quantized latent representation y back to obtain the reconstructed image x = gs(y). The framework is trained with the rate-distortion loss function, i.e., £ = D + R, where D is the distortion between x and x, R is the rate calculated or estimated from the quantized representation y, and A is the Lagrange multiplier. It should be noted that D can be calculated in either pixel domain or perceptual domain. All existing research works follow this prototype and the difference might only be the network structure or loss function.Hyper prior modelIn the transform coding approach to image compression, the encoder subnetwork transforms the image vector x using a parametric analysis transform ga(x, 0p) into a latent representation y, which is then quantized to form y. Because y is discrete-valued, it can be losslessly compressed using entropy coding techniques such as arithmetic coding and transmitted as a sequence of bits. As evident from the middle left and middle right image of Fig. 2, there are significant spatial dependencies among the elements of y. Notably, their scales (middle right image) appear to be coupled spatially. An additional set of random variables z can be introduced to capture the spatial dependencies and to further reduce the redundancies. In this case the image compression network is depicted in Fig. 3.In Fig 3, the left hand of the models is the encoder gaand decoder gs. The right-hand side is the additional hyper encoder haand hyper decoder hsnetworks that are used to obtain z. In this architecture the encoder subjects the input image x to ga, yielding the responses y with spatially varying standard deviations. The responses y are fed into ha, summarizing the distribution of standard deviations in z. z is then quantized (z), compressed, and transmitted as side information. The encoder then uses the quantized vector z to estimate a, the spatial distribution of standard deviations, and uses it to compress and transmit the quantized image representation y . The decoder first recovers z from the compressed signal. It then uses hsto obtain <r, which provides it with the correct probability estimates to successfully recover y as well. It then feeds y into gsto obtain the reconstructed image.When the hyper encoder and hyper decoder are added to the image compression network, the spatial redundancies of the quantized latent y are reduced. The rightmost image in Fig. 2 correspond to the quantized latent when hyper encoder / decoder are used. Compared to middle right image, the spatial redundancies are significantly reduced, as the samples of the quantized latent are less correlated.In Fig. 2: Left: an image from the Kodak dataset. Middle left: visualization of a latent representation y of that image. Middle right: standard deviations a of the latent. Right: latents y after the hyper prior (hyper encoder and decoder) network is introduced.Fig. 3 illustrates Network architecture of an autoencoder implementing the hyperprior model. The left side shows an image autoencoder network, the right side corresponds to the hyperprior subnetwork. The analysis and synthesis transforms are denoted as gaand ga. Q represents quantization, and AE, AD represent arithmetic encoder and arithmetic decoder, respectively. The hyperprior model consists of two subnetworks, hyper encoder (denoted with ha) and hyper decoder (denoted with hs). The hyper prior model generates a quantized hyper latent (z) whichcomprises information about the probability distribution of the samples of the quantized latent y. z is included in the bitsteam and transmitted to the receiver (decoder) along with y.Context modelAlthough the hyper prior model improves the modelling of the probability distribution of the quantized latent y, additional improvement can be obtained by utilizing an autoregressive model that predicts quantized latents from their causal context (Context Model).The term auto-regressive means that the output of a process is later used as input to it. For example the context model subnetwork generates one sample of a latent, which is later used as input to obtain the next sample.Fig. 4 is a schematic diagram illustrating an example combined model configured to jointly optimize a context model along with a hyperprior and the autoencoder. The following Table 1 illustrates meaning of different symbols.Table 1 - Illustration of symbolsA joint architecture can be utilized where both hyper prior model subnetwork (hyper encoder and hyper decoder) and a context model subnetwork are utilized. The hyper prior and the context model are combined to learn a probabilistic model over quantized latents y, which is then used for entropy coding. As depicted in Fig. 4, the outputs of context subnetwork and hyper decoder subnetwork are combined by the subnetwork called Entropy Parameters, which generates the mean and scale (or variance) o parameters for a Gaussian probability model. The gaussian probability model is then used to encode the samples of the quantized latents into bitstream with the help of the arithmetic encoder (AE) module. In the decoder the gaussian probability model is utilized to obtainthe quantized latents y from the bitstream by arithmetic decoder (AD) module.Fig 4 illustrates the combined model jointly optimizes an autoregressive component that estimates the probability distributions of latents from their causal context (Context Model) along with a hyperprior and the underlying autoencoder. Real-valued latent representations are quantized (Q) to create quantized latents (y) and quantized hyper-latents (z), which are compressed into a bitstream using an arithmetic encoder (AE) and decompressed by an arithmetic decoder (AD). The highlighted region corresponds to the components that are executed by the receiver (i.e. a decoder) to recover an image from a compressed bitstream.Typically the latent samples are modeled as gaussian distribution or gaussian mixture models (not limited to). According to Fig. 4, the context model and hyper prior are jointly used to estimate the probability distribution of the latent samples. Since a gaussian distribution can be defined by a mean and a variance (aka sigma or scale), the joint model is used to estimate the mean and variance (denoted as and <r).Gained variational autoencoders (G-VAE)Typically, neural network-based image / video compression methodologies need to train multiple models to adapt to different rates. Gained variational autoencoders (G-VAE) is the variational autoencoder with a pair of gain units , which is designed to achieve continuously variable rate adaptation using a single model. It comprises of a pair of gain units, which are typically inserted to the output of encoder and input of decoder. The output of the encoder is defined as the latent representation y G Rc*h*wwhere c, h, w represent the number of channels, the height and width of the latent representation. Each channel of the latent representation is denoted aswhere i = 0, 1, ... , c — 1. A pair of gain units include a gain matrix M G Rc*nand an inverse gain matrix, where n is the number of gain vectors. The gain vector can be denoted as ms=where s denotes the index of the gain vectors in the gain matrix.The motivation of gain matrix is similar to the quantization table in JPEG by controlling the quantization loss based on the characteristics of different channels. To apply the gain matrix to the latent representation, each channel is multiplied with the corresponding value in a gain vector. ys= y © mswhere © is channel-wise multiplication, i.e., ys^ = y^ X as^, and as^ is the i-th gain value in the gain vector ms. The inverse gain matrix used at the decoder side can be denoted as M' G Rc*n, which consists of n inverse gain vectors, i.e., M' =eR The inverse gain process is expressed as: y's= y ©mswhere y is the decoded quantized latent representation and y<J is the inversely gained quantized latent representation, which will be fed into the synthesis network.To achieve continuous variable rate adjustment, interpolation is used between vectors. Given two pairs of gain vectors {mt, mt'} and {mr, mr' }, the interpolated gain vector can be obtained via the following equations.where I E R is an interpolation coefficient, which controls the corresponding bit rate of the generated gain vector pair. Since I is a real number, an arbitrary bit rate between the given two gain vector pairs can be achieved.The encoding process using joint auto-regressive hyper prior modelThe fig 4. corresponds to the state of the art compression method. In this section and the next, the encoding and decoding processes will be described separately.The Fig. 5 depicts the encoding process. The input image is first processed with an encoder subnetwork. The encoder transforms the input image into a transformed representation called latent, denoted by y. y is then input to a quantizer block, denoted by Q, to obtain the quantized latent (y ). y is then converted to a bitstream (bitsl) using an arithmetic encoding module (denoted AE). The arithmetic encoding block converts each sample of the y into a bitstream (bitsl) one by one, in a sequential order.The modules hyper encoder, context, hyper decoder, and entropy parameters subnetworks are used to estimate the probability distributions of the samples of the quantized latent y. the latent y is input to hyper encoder, which outputs the hyper latent (denoted by z). The hyper latent is then quantized (z) and a second bitstream (bits2) is generated using arithmetic encoding (AE) module. The factorized entropy module generates the probability distribution, that is used to encode the quantized hyper latent into bitstream. The quantized hyper latent includes information about the probability distribution of the quantized latent (y).The Entropy Parameters subnetwork generates the probability distribution estimations, that are used to encode the quantized latent y. The information that is generated by the Entropy Parameters typically include a mean g and scale (or variance) a parameters, that are together used to obtain a gaussian probability distribution. A gaussian distribution of a random variable x is defined as f (x) = a ) wherein the parameter g is the mean or expectation of the distribution (and also its median and mode), while the parameter a is its standard deviation (or variance, or scale). In order to define a gaussian distribution, the mean and the variance need to be determined. In anexisting design, the entropy parameters module are used to estimate the mean and the variance values.The subnetwork hyper decoder generates part of the information that is used by the entropy parameters subnetwork, the other part of the information is generated by the autoregressive module called context module. The context module generates information about the probability distribution of a sample of the quantized latent, using the samples that are already encoded by the arithmetic encoding (AE) module. The quantized latent y is typically a matrix composed of many samples. The samples can be indicated using indices, such as y[i,j,k] or y[i,j] depending on the dimensions of the matrix y. The samples y[i,j] are encoded by AE one by one, typically using a raster scan order. In a raster scan order the rows of a matrix are processed from top to bottom, wherein the samples in a row are processed from left to right. In such a scenario (wherein the raster scan order is used by the AE to encode the samples into bitstream), the context module generates the information pertaining to a sample y[i,j ], using the samples encoded before, in raster scan order. The information generated by the context module and the hyper decoder are combined by the entropy parameters module to generate the probability distributions that are used to encode the quantized latent y into bitstream (bitsl).Finally the first and the second bitstream are transmitted to the decoder as result of the encoding process.It is noted that the other names can be used for the modules described above.In the above description, the all of the elements in Fig. 5 are collectively called encoder. The analysis transform that converts the input image into latent representation is also called an encoder (or auto-encoder).The decoding process using joint auto-regressive hyper prior modelThe Fig. 6 depicts the decoding process separately.In the decoding process, the decoder first receives the first bitstream (bitsl) and the second bitstream (bits2) that are generated by a corresponding encoder. The bits2 is first decoded by the arithmetic decoding (AD) module by utilizing the probability distributions generated by the factorized entropy subnetwork. The factorized entropy module typically generates the probability distributions using a predetermined template, for example using predetermined mean and variance values in the case of gaussian distribution. The output of the arithmetic decoding process of the bits2 is z, which is the quantized hyper latent. The AD process reverts to AE process that was applied in the encoder. The processes of AE and AD are lossless, meaning that the quantized hyper latent z that was generated by the encoder can be reconstructed at the decoder without any change. After obtaining of z, it is processed by the hyper decoder, whose output is fed to entropyparameters module. The three subnetworks, context, hyper decoder and entropy parameters that are employed in the decoder are identical to the ones in the encoder. Therefore the exact same probability distributions can be obtained in the decoder (as in encoder), which is essential for reconstructing the quantized latent y without any loss. As a result the identical version of the quantized latent y that was obtained in the encoder can be obtained in the decoder.After the probability distributions (e.g. the mean and variance parameters) are obtained by the entropy parameters subnetwork, the arithmetic decoding module decodes the samples of the quantized latent one by one from the bitstream bitsl. From a practical standpoint, autoregressive model (the context model) is inherently serial, and therefore cannot be sped up using techniques such as parallelization.Finally the fully reconstructed quantized latent y is input to the synthesis transform (denoted as decoder in Fig. 6) module to obtain the reconstructed image.In the above description, the all of the elements in Fig. 6 are collectively called decoder. The synthesis transform that converts the quantized latent into reconstructed image is also called a decoder (or auto-decoder).Neural networks for video compressionSimilar to conventional video coding technologies, neural image compression serves as the foundation of intra compression in neural network-based video compression, thus development of neural network-based video compression technology comes later than neural network-based image compression but needs far more efforts to solve the challenges due to its complexity. Starting from 2017, a few researchers have been working on neural network-based video compression schemes. Compared with image compression, video compression needs efficient methods to remove interpicture redundancy. Inter-picture prediction is then a crucial step in these works. Motion estimation and compensation is widely adopted but is not implemented by trained neural networks until recently.Studies on neural network-based video compression can be divided into two categories according to the targeted scenarios: random access and the low-latency. In random access case, it requires the decoding can be started from any point of the sequence, typically divides the entire sequence into multiple individual segments and each segment can be decoded independently. In low-latency case, it aims at reducing decoding time thereby usually merely temporally previous frames can be used as reference frames to decode subsequent frames.PreliminariesAlmost all the natural image / video is in digital format. A grayscale digital image can be represented by x E IDmxn, where ID is the set of values of a pixel, m is the image height and n isthe image width. For example, ID = {0, 1, 2, ... ,255} is a common setting and in this case | | = 256 = 28, thus the pixel can be represented by an 8-bit integer. An uncompressed grayscale digital image has 8 bits-per-pixel (bpp), while compressed bits are definitely less.A color image is typically represented in multiple channels to record the color information. For example, in the RGB color space an image can be denoted by x E ]D)mxnx3with three separate channels storing Red, Green and Blue information. Similar to the 8-bit grayscale image, an uncompressed 8-bit RGB image has 24 bpp. Digital images / videos can be represented in different color spaces. The neural network-based video compression schemes are mostly developed in RGB color space while the traditional codecs typically use YUV color space to represent the video sequences. In YUV color space, an image is decomposed into three channels, namely Y, Cb and Cr, where Y is the luminance component and Cb / Cr are the chroma components. The benefits come from that Cb and Cr are typically down sampled to achieve pre-compression since human vision system is less sensitive to chroma components.A color video sequence is composed of multiple color images, called frames, to record scenes at different timestamps. For example, in the RGB color space, a color video can be denoted by X = {%0, %-L, ... , xT-1} where T is the number of frames in this video sequence, x 6 IDmxn. [f m = 1080, n = 1920, | | = 28, and the video has 50 frames-per-second (fps), then the data rate of this uncompressed video is 1920 x 1080 x 8 x 3 x 50 = 2,488,320,000 bits-per-second (bps), about 2.32 Gbps, which needs a lot storage thereby definitely needs to be compressed before transmission over the internet.Usually the lossless methods can achieve compression ratio of about 1.5 to 3 for natural images, which is clearly below requirement. Therefore, lossy compression is developed to achieve further compression ratio, but at the cost of incurred distortion. The distortion can be measured by calculating the average squared difference between the original image and the reconstructed image, i.e., mean-squared-error (MSE). For a grayscale image, MSE can be calculated with the following equation.Accordingly, the quality of the reconstructed image compared with the original image can be measured by peak signal-to-noise ratio (PSNR):where max(ID) is the maximal value in ID, e.g., 255 for 8-bit grayscale images. There are other quality evaluation metrics such as structural similarity (SSIM) and multi-scale SSIM (MS- SSIM).To compare different lossless compression schemes, it is sufficient to compare either the compression ratio given the resulting rate or vice versa. However, to compare different lossy compression methods, it has to take into account both the rate and reconstructed quality. For example, to calculate the relative rates at several different quality levels, and then to average the rates, is a commonly adopted method; the average relative rate is known as Bjontegaard’s deltarate (BD-rate). There are other important aspects to evaluate image / video coding schemes, including encoding / decoding complexity, scalability, robustness, and so on.Separate processing of luma and chroma components of an imageFig. 7 illustrates the decoding process according to some example embodiments of the present disclosure. According to one implementation, the luma and chroma components of an image can be decoded using separate subnetworks. In Fig. 7, the luma component of the image is processed by the subnetwoks “Synthesis”, “Prediction fusion”, “Mask Conv”, “Hyper Decoder”, “Hyper scale decoder” etc. Whereas the chroma components are processed by the subnetworks: “Synthesis UV”, “Prediction fusion UV”, “Mask Conv UV”, “Hyper Decoder UV”, “Hyper scale decoder UV” etc.A benefit of the above separate processing is that the computational complexity of the processing of an image is reduced by application of separate processing. Typically in neural network based image and video decoding, the computational complexity is proportional to the square of the number of feature maps. If the number of total feature maps is equal to 192 for example, computational complexity will be proportional to 192x192. On the other hand if the feature maps are divided into 128 for luma and 64 for chroma (in the case of separate processing), the computational complexity is proportional to 128x128 + 64x64, which corresponds to a reduction in complexity by 45%. Typically the separate processing of luma and chroma components of an image does not result in a prohibitive reduction in performance, as the correlation between the luma and chroma components are typically very small.The processing (Decoding process) in Fig. 7 can be explained below:1. Firstly, the factorized entropy model is used to decode the quantized latents for luma and chroma, i.e., z and zuvin Fig. 7.2. The probability parameters (e.g. variance) generated by the second network are used to generate a quantized residual latent by performing the arithmetic decoding process.3. The quantized residual latent is inversely gained with the inverse gain unit (iGain) as shown in orange color in Fig. 7. The outputs of the inverse gain units are denoted as w and wuvfor luma and chroma components, respectively.4. For the luma component, the following steps are performed in a loop until all elements ofy are obtained: a. A first subnetwork is used to estimate a mean value parameter of a quantized latent (y), using the already obtained samples of y. b. The quantized residual latent w and the mean value are used to obtain the next element of y.5. After all of the samples of y are obtained, a synthesis transform can be applied to obtain the reconstructed image.6. For chroma component, step 4 and 5 are the same but with a separate set of networks.7. The decoded luma component is used as additional information to obtain the chroma component. Specifically, the Inter Channel Correlation Information filter sub-network (ICCI) is used for chroma component restoration. The luma is fed into the ICCI subnetwork as additional information to assist the chroma component decoding.8. Adaptive color transform (ACT) is performed after the luma and chroma components are reconstructed.The module named ICCI is a neural -network based postprocessing module. The example embodiments of the present disclosure are not limited to the UCCI subnetwork, any other neural network based postprocessing module might also be used.An exemplary implementation of some example embodiments of the present disclosure is depicted in Fig. 7 (the decoding process). The framework comprises two branches for luma and chroma components respectively. In each of the branch, the first subnetwork comprises the context, prediction and optionally the hyper decoder modules. The second network comprises the hyper scale decoder module. The quantized hyper latent are z and zuv. The arithmetic decoding process generates the quantized residual latents, which are further fed into the iGain units to obtain the gained quantized residual latents w and wuv.After the residual latent is obtained, a recursive prediction operation is performed to obtain the latent y and yuv. The following steps describe how to obtain the samples of latent y[: , i, / ], and the chroma component is processed in the same way but with different networks.1. An autoregressive context module is used to generate first input of a prediction module using the samples y[: ,m,n] where the (m, n) pair are the indices of the samples of the latent that are already obtained.2. Optionally the second input of the prediction module is obtained by using a hyper decoder and a quantized hyper latent zj.3. Using the first input and the second input, the prediction module generates the mean value mean[\ , i,j].4. The mean value mean[-. , t,j and the quantized residual latent w[: , i, / ]are added together to obtain the latent y[: , l,j].5. The steps 1-4 are repeated for the next sample.Whether to and / or how to apply at least one method disclosed in the document may be signaled from the encoder to the decoder, e.g. in the bitstream.Alternatively, whether to and / or how to apply at least one method disclosed in the document may be determined by the decoder based on coding information, such as dimensions, color format, etc. Alternative or additionally, the modules named MSI, MS2 or MS3+0 (in Fig. 7), might be included in the processing flow. The said modules might perform an operation to their input by multiplying the input with a scalar or adding an adding an additive component to the input to obtain the output. The scalar or the additive component that are used by the said modules might be indicated in a bitstream.The module named RD or the module named AD in Fig. 7 might be an entropy decoding module. It might be a range decoder or an arithmetic decoder or the like.The example embodiments of the present disclosure described herein are not limited to the specific combination of the units exemplified in Fig. 7. Some of the modules might be missing and some of the modules might be displaced in processing order. Also additional modules might be included. For example:1. The ICCI module might be removed. In that case the output of the Synthesis module and the Synthesis UV module might be combined by means of another module, that might be based on neural networks.2. One or more of the modules named MSI, MS2 or MS3+0 might be removed. The core of the proposed solution is not affected by the removing of one or more of the said scaling and adding modules.In Fig. 7, other operations that are performed during the processing of the luma and chroma components are also indicated using the star symbol. These processes are denoted as MSI, MS2, MS3+0. These processing might be, but not limited to, adaptive quantization, latent sample scaling, and latent sample offsetting operations. For example, in an adaptive quantization process might correspond to scaling of a sample with multiplier before the prediction process, wherein the multiplier is predefined or whose value is indicated in the bitstream. The latent scaling process might correspond to the process where a sample is scaled with a multiplier after the prediction process, wherein the value of the multiplier is either predefined or indicated in the bitstream. The offsetting operation might correspond to adding an additive element to the sample, again wherein the value of the additive element might be indicated in the bitstream or inferred or predetermined.Another operation might be tiling operation, wherein samples are first tiled (grouped) into overlapping or non-overlapping regions, wherein each region is processed independently. For example the samples corresponding to the luma component might be divided into tiles with a tile height of 20 samples, whereas the chroma components might be divided into tiles with a tile height of 10 samples for processing.Another operation might be application of wavefront parallel processing. In wavefront parallel processing, a number of samples might be processed in parallel, and the amount of samples that can be processed in parallel might be indicated by a control parameter. The said control parameter might be indicated in the bitstream, be inferred, or can be predetermined. In the case of separate luma and chroma processing, the number of samples that can be processed in parallel might be different, hence different indicators can be signalled in the bitstream to control the operation of luma and chrome processing separately.2.4. The JPEG Al image coding standardThe existing design utilizes some NN-based image coding methods described mentioned above. Some of the features in the existing design are described or summarized below. The numbers in the parentheses are section numbers in one existing design.2.4.1. (9.2) Code stream layoutThe overall syntax structure of an image is:Each code stream starts with a 16-bit marker. All markers used in this specification are as follows:2.4.2. (9.3) Picture headerThis sub-stream contains information about image height H, width W, latent space tiles location and sizes, control flags for each tool, scaling factors for primary and secondary component, modelldx - learnable model index and displacement for rate control parameters (flYfor primary and / 3UVfor secondary component).2.4.2.1 (9.3.1) Syntax table2.4.2.2 (9.3.1.1) Model header syntax and color transform header syntax2.4.2.3 (9.3.2) Picture header semantics Following service information is signalled: picture_header_size is the number of bytes in the picture header excluding the first two-byte marker; img width plus 64 specifies width of an input picture (from 64 to 65600); img height plus 64 specifies height of the input picture (from 64 to 65600); picture_format is a data format of the output picture (YUV420 = 0, YUV444 = 1, sRGB = 2, YUV422 = 3); bit_depth is a bit-depth the output picture (“0” corresponds to 8 and “1” corresponds to 10); color_transform_offset[i] is an offset for color transformation If not present (color transform enable is false) then default ITU-R BT.709 colour transform is used (refer to section 7.8).2.4.3. (9.4) Tools headerThis optional sub-stream contains information about tools. When the tools_header() marker segment is not present in the bitstream, the following tool enabling flags are set to be 0: rvs enable flag, Isbs enable flag, grfs enable flag, gain_3D_enable_flag, icci enable flag, LEF enabled flag, EFE upsampler enabled flag, and EFE nonlinear filter enabled flag.tools_header_size is the number of bytes in the tools header excluding the first two-byte marker; rvs enable flag - is a flag used in the RVS for each color component. 0 indicates RVS disabled, 1 indicates RVS turn on.3. ProblemsThe existing design has the following problems:1) The syntax and semantics for the tools header, including the TOH marker, is inconsistent, as the syntax is specified in a manner that the tools header, including the TOH marker, is not optional, while in the semantics says it is optional.2) The bit depth of the output picture is signalled using a one-bit syntax element, with the values 0 and 1 specifying 8 bits and 10 bits, respectively. However, this makes it difficult or impossible to add support of other bit depths, e.g., 12, 14, or 16 bits, in a future version of the JPEG Al standard after the finalization of the first version, in a backward-compatible manner.3) There lacks a mechanism for signalling of profile and level information, in particular sinceit is expected that a JPEG Al codestream may conform to a stream profile and a number of decoder profiles.4) There lacks a mechanism for indicating a specify a restriction based on an image quality (or fidelity) based on a level definition and signalling.5) There lacks a mechanism for indicating a decoder version, which might be related to the values of the constants that are used in the decoding process, e.g., the values of the weights (multiplicative coefficients) and / or the biases (additive coefficients) of a neural network based model.4. Detailed SolutionsTo solve the above-described problems, methods as summarized below are disclosed. The solutions should be considered as examples to explain the general concepts and should not be interpreted in a narrow way. Furthermore, these solutions can be applied individually or combined in any manner.1) In one example, in a JPEG Al codestream, the information about tools, e.g., contained in the tools header syntax structure, is directly included in the picture header and as part of the picture header sub-stream instead of in its own sub-stream. a. In one example, additionally, the TOH marker and the tools header size syntax elements are not signalled in the tools header syntax structure. b. In one example, alternatively, the tools header is kept as a sub-stream, thus not part of picture header, and the TOH marker is always present and clarified as mandatory (i.e., not optional). c. In one example, alternatively, the syntax for signalling of tools header is changed such that the tools header is an optional sub-stream. i. In one example, whether to have the tools header may be indicated in a bitstream, e.g., by a 1 -bit flag.1. In one example, the syntax for signalling of tools header is changed by adding a syntax element (e.g., a presence flag) directly in the picture() syntax structure or in the picture header syntax structure. a. Alternatively, furthermore, the value 1 of the flag specifies that the information about tools is explicitly signalled and the value 0 of the flag specifies that the information about tools is not explicitly signalled and one or more pieces of the information are inferred.ii. In one example, whether to have the tools header may be determined by a certain condition, e.g., whether the next N bytes after parsing the picture header syntax structure is equal to the value of TOH marker.1. In one example, the syntax for signalling of tools header is changed by adding a check of the next two bytes after parsing the picture header syntax structure, and explicitly signal the information about tools only when the value of the next two bytes after parsing the picture header syntax structure is equal to the value of TOH marker. Additionally, when the information about tools is not explicitly signalled, one or more pieces of the information are inferred. d. In one example, alternatively, the syntax for signalling of tools header is changed by adding a presence flag in the picture header syntax structure and, only when the flag is equal to 1, the information about tools, without the TOH marker and the size of the tools information, is signalled in the picture header syntax structure, thus not as a sub-stream of itself. e. In one example, multiple tools headers may be signaled in a bitstream. f. In one example, an index may be signaled in a tools header. i. In one example, a tools header index may be signaled in a second coding unit to indicate which tools header is used for the second coding unit.1. For example, the second coding unit may be a picture header.) In one example, in a JPEG Al codestream, the bit depth of the output picture is signalled using a bit depth syntax element with a length greater than one bit. a. In one example, the bit depth syntax element is of three bits, with the values “0”, “1”, “2”, “3”, and "4" correspond to 8, 10, 12, 14, and 16 bits, respectively, and other values are reserved. ) In one example, a JPEG Al codestream includes one or more syntax elements signalling the information of profile and level, wherein the profile information comprises an indication of a stream profile to which the codestream conforms and an indication of one or more supported decoder profiles provided by the codestream. a. In one example, the indication of the stream profile comprises an 8-bit syntax element, e.g., named stream_profile_idc. b. In one example, the indication of one or more supported decoder profiles comprises an indication of a number of decoder profiles followed a list of decoder profile indications each indicating a decoder profile.i. In one example, the indication of the number of decoder profiles comprises an 8-bit syntax element, e.g., named num_decoder_profiles_minusl. ii. In one example, each of the decoder profile indications comprises an 8-bit syntax element, e.g., named decoder_profile_idc[ i ]. c. In one example, the information of profile and level includes an indication of a level to which the codestream conforms. i. In one example, the indication of the level comprises an 8-bit syntax element, e.g., named level idc. d. In one example, the information of profile and level is signalled as part of the picture header. i. In one example, the information of profile and level is signalled in a profile and level syntax structure that is included in the picture header. e. In one example, the information of profile and level includes an indication of a stream level to which the codestream conforms. f. In one example, the information of profile and level includes an indication of one or more supported decoder levels provided by the codestream. i. In one example, a decoder level is indicated specifically for a decoder profile and may be referred to as the level associated with a supported decoder profile provided by the codestream. ii. In one example, the indication of a decoder level comprises an 8-bit syntax element, e.g., named decoder level idcf i ]. g. In another example, an indication of a stream level (e.g. stream level idc) is included in the bitstream. The stream level might specify the level that the stream conforms to. h. In another example at least 2 level indications are included in the bitstream specifying different types of restrictions and / or capabilities. i. According to one example, the restriction and / or capability that is specified by the first level indication might be different from the second level indication.1. As an example the first level indication might specify a restriction based on a picture size, and the second level indication might specify a restriction based on an image quality (or fidelity).2. In another example a first level indication might specify a restriction based on a bitstream size, and the second level indication mightspecify a restriction based on the value of a syntax element of the bitstream. ii. According to another example, the restriction and / or capability that is specified by the first level indication might be overwritten by the second level indication. i. In another example an indication to a decoder version (e.g. decoder version idc) might be included in the bitstream. The decoder version might specify version related parameters. For example the version related parameters might be related to the values of the constants that are used in the decoding process such as: i. The values of the weights (multiplicative coefficients) of a neural network based model. ii. The values of the biases (additive coefficients) of a neural network based model. iii. The values of the constant parameters that are used in the decoding process. j. In one example, one or more of the above-mentioned profile, level, or decoder version syntax elements are coded using 16 bits instead of 8 bits. k. In one example, the profile or level may be signaled in a conditional way. i. For example, the valid value range of the profile may depend on dimensions of the picture. ii. For example, the valid value range of the level may depend on dimensions of the picture. iii. For example, the valid value range of the level may depend on the profile. iv. For example, the valid value range of the profile may depend on the level. l. In one example, whether to and / or how to signaled a syntax element may depend on the signaled profile or level. i. For example, a syntax element is signaled only if the signaled profile is a certain value or in a certain range. ii. For example, a syntax element is signaled only if the signaled level is a certain value or in a certain range. iii. For example, the value range of a syntax element may depend on the signaled profile / level. ) In above examples, the JPEG Al may be replaced by other image / video coding framework, e.g., end to end image / video compression solutions, hybrid image / video compression solutions with NN-based coding tools embedded.5. EmbodimentsBelow are some example embodiments for some of the solution items summarized above in Section 4.Most relevant parts that have been added or modified are shown by using bolded words (e.g., this format indicates added text), and some of the deleted parts are shown by using words in italics between double curly brackets (e.g., {{this format indicates deleted text}}). There may be some other changes that are not highlighted. It should be understood that only markings in this section are intended to emphasize at least part of proposed changes.5.1. Embodiment 1 This embodiment is for the solution items 1, l.a, 2, 2. a, 3, 3. a, 3.b, 3.b.i, 3.b.ii, 3.c, 3.c.i, 3.d, and3.d.i summarized above in Section 4.5.1.1. (9.2) Code stream layoutThe overall syntax structure of an image is:Each code stream starts with a 16-bit marker. All markers used in this specification are as follows:5.1.2. (9.3) Picture headerThis sub-stream contains information about image height H, width W, latent space tiles location and sizes, control flags for each tool, scaling factors for primary and secondary component, modelldx - learnable model index and displacement for rate control parameters (flYfor primary and / 3UVfor secondary component).5.1.2.1 (9.3.1) Syntax table5.1.2.2 (9.3.1.1) Model header syntax and color transform header syntax5.1.2.3 (9.3.1.2) Profile and level syntax5.1.2.4 (9.3.2) Picture header semanticsFollowing service information is signalled: picture header size is the number of bytes in the picture header excluding the first two-byte marker;img width plus 64 specifies width of an input picture (from 64 to 65600); img height plus 64 specifies height of the input picture (from 64 to 65600); picture format is a data format of the output picture (YUV420 = 0, YUV444 = 1, sRGB = 2, YUV422 = 3);{{bit depth is a bit-depth the output picture (“0” corresponds to 8 and “1 ” corresponds to 10);}} bit depth idc specifies the bit-depth the output picture (“0”, “1”, “2”, “3”, and "4" correspond to 8, 10, 12, 14, and 16 bits, respectively; other values are reserved); color transform offsetfi] is an offset for color transformation If not present (color transform enable is false) then default ITU-R BT.709 colour transform is used (refer to section 7.8). stream profile idc indicates the stream profile to which the codestream conforms. num decoder profiles minusl plus 1 specifies the number of supported decoder profiles provided by the codestream. decoder_profile_idc[ i ] indicates the i-th supported decoder profiles provided by the codestream. level idc indicates the level to which the codestream conforms.5.1.3. (9.4) Tools header{{This optional sub-stream contains information about tools. When the tools header() marker segment is not present in the bitstream, the following tool enabling flags are set to be 0: rvs enable flag, Isbs enable flag, grfs enable flag, gain 3D enable flag, icci enable flag, LEF enabled Jlag, EFE upsampler enabled Jlag, and EFE nonlinear filter enabled Jlag. }}This syntax structure contains information about tools.{{tools header size is the number of bytes in the tools header excluding the first two-byte marker;}} rvs enable flag - is a flag used in the RVS for each color component. 0 indicates RVS disabled, 1 indicates RVS turn on.5.2. Emb odiment 2Embodiment 2 provides another example of the solution enclosed in Section 4.5.1.2.3 (9.3.1.2) Profile and level syntaxIn the example in embodiment 2, an additional indication is included (decoder version idc) compared to the embodiment 1. This syntax element might indicate a version of the decoder.5.3. Embodiment 3Embodiment 3 provides another example of the solution enclosed in Section 4. 5.1.2.3 (9.3.1.2) Profile and level syntaxIn the example in embodiment 3, an additional indication is included (stream level idc) comparedto the embodiment 2. And furthermore the name of the syntax element level idc is changed as decoder level idc to make the distinction between stream level idc.The decoder level idc and stream level idc might jointly indicate the conformance of the bitstream or conformance of the decoder. The stream level idc might indicate restrictions of capabilities that are joint among all of the decoder profiles. In another example the stream level idc might indicate restrictions or capabilities that apply to the bitstream. The decoder level idc on the other hand might indicate restrictions or capabilities that are specific to the decoder profile (that is indicated by decoder_profile_idc). In the case when a bitstream can comply to multiple decoder profiles, using a pair of levels (eg. stream level idc and decoder level idc) can help distinguishing common restrictions / capabilities from the decoder profile specific restrictions / capabilities.5.4. Emb odiment 4This embodiment is for the invention items 3, 3. a, 3.b, 3.b.i, 3.b.ii, 3.d, 3.d.i, 3.f, 3.f.i, and 3.f.ii summarized above in Section 4.5.1.2.3 (9.3.1.2) Profile and level syntax5.1.2.4 (9.3.2) Picture header semanticsFollowing service information is signalled: color transform offsetfi] is an offset for color transformation If not present (color transform enable is false) then default ITU-R BT.709 colour transform is used (refer to section 7.8). stream profile idc indicates the stream profile to which the codestream conforms, num decoder profiles minusl plus 1 specifies the number of supported decoder profiles provided by the codestream. decoder_profile_idc[ i ] indicates the i-th supported decoder profile provided by thecodestream. decoder_level_idc[ i ] indicates the level associated with the i-th supported decoder profile provided by the codestream.

[0034] More details of the embodiments of the present disclosure will be described below which are related to neural network-based visual data coding. As used herein, the term “visual data” may refer to an image, a video, a picture in a video, or any other visual data suitable to be coded. To solve the above problems and some other problems not mentioned, visual data processing solutions as described below are disclosed. The embodiments of the present disclosure should be considered as examples to explain the general concepts and should not be interpreted in a narrow way. Furthermore, these embodiments can be applied individually or combined in any manner.

[0035] Fig. 8 illustrates a flowchart of a method 800 for visual data processing in accordance with some embodiments of the present disclosure. At 802, a conversion between the visual data and a codestream of the visual data is performed with a neural network (NN)-based model. For example, a codestream may comprise a sequence of bits. In addition, the codestream may further comprise associated codes which are used as markers. As used herein, the codestream may also be referred to as a bitstream.

[0036] In some embodiments, the conversion may include encoding the visual data into the codestream. Additionally or alternatively, the conversion may include decoding the visual data from the codestream. By way of example rather than limitation, the decoding model shown in Fig. 6 may be employed for decoding the visual data from the bitstream.

[0037] As used herein, an NN-based model may be a model based on neural network technologies. For example, an NN-based model may specify sequence of neural network modules (also called architecture) and model parameters. The neural network module may comprise a set of neural network layers. Each neural network layer specifies a tensor operation which receives and outputs tensor, and each layer has trainable parameters. It should be understood that the possible implementations of the NN-based model described here are merely illustrative and therefore should not be construed as limiting the present disclosure in any way.

[0038] In addition, the codestream comprises a first indication indicating a stream profile to which the codestream conforms. As used herein, a stream profile may refer to a subset of the entire bitstream syntax that is specified in advance, such as in a recommendation or standard document. For example, the first indication may be represented asstream profile idc or the like. For example, the first indication may be comprised in a picture header in the codestream. By way of example, the number of bits used for the first indication may be predetermined, such as 4, 8, or the like.

[0039] In view of the above, the codestream comprises a first indication indicating a stream profile to which the codestream conforms. Compared with the conventional solution lacking such an indication, the proposed method can provide a mechanism for signaling of stream profile information, and thus can better support the application of different stream profiles. Thereby, the coding flexibility can be improved.

[0040] In some embodiments, the codestream may further comprise one or more second indications indicating one or more supported decoder profiles provided by the codestream. As used herein, a decoder profile may define the capabilities of a decoder, i.e. a subset of tools that allow to obtain the decoded visual data. Different decoded qualities may be achieved for different decoder profiles using the same stream compliant with a specific stream profile. This means that interoperability may not be broken between decoders that use the same stream profile but use different decoder profiles. Within the bounds imposed by the syntax of a given stream and decoder profile it is still possible to obtain a very large variation in the performance of encoders and decoders depending upon the values taken by syntax elements in the bitstream.

[0041] For example, one of the one or more second indications that indicates the i-th supported decoder profile among the one or more supported decoder profiles may be represented as decoder_profile_idc[ i ], and i may be an integer. It should be noted that the name of an indication mentioned herein is merely illustrative and such an indication may also be denoted by any suitable string. The scope of the present disclosure is not limited in this respect. For example, the number of bits used for each of the one or more second indications may be predetermined, such as 4, 8 or the like. In addition, the one or more second indications may be comprised in a picture header in the codestream.

[0042] In some embodiments, the codestream may further comprise a third indication indicating the number of supported decoder profiles provided by the codestream. In this case, the one or more second indications may follow the third indication in the codestream. For example, a value of the third indication plus a predetermined number (such as 1, 2 or the like) may be equal to the number of the supported decoder profiles provided by the codestream. In a case where the predetermined number is 1, the third indication may be represented as num decoder profiles minusl, or the like. The number of bits used for the third indication may be predetermined, such as 4, 8 or the like. In addition, the thirdindication may be comprised in a picture header in the codestream.

[0043] Compared with the conventional solution, the proposed method can provide a mechanism for signaling of decoder profile information, and thus can better support the application of different decoder profiles. Thereby, the coding flexibility can be improved.

[0044] In some embodiments, the codestream may further comprise a fourth indication indicating a level to which the codestream conforms. As used herein, a level may refer to a specified set of constraints imposed on values of the syntax elements in the bitstream. Some of these constraints are expressed as simple limits on values, while others take the form of constraints on arithmetic combinations of values. A lower level specified is more constrained than a higher level.

[0045] For example, the fourth indication may be represented as level idc. The number of bits used for the fourth indication may be predetermined, such as 4, 8 or the like. In addition, the fourth indication may be comprised in a picture header in the codestream.

[0046] Compared with the conventional solution, the proposed method can provide a mechanism for signaling of level information, and thus can better support the application of different decoder profiles. Thereby, the coding flexibility can be improved.

[0047] In some embodiments, the codestream may further comprise a fifth indication indicating a bit-depth of an output picture of the conversion, and the number of bits used for the fifth indication is greater than one. By way of example, the number of bits used for the fifth indication may be two, three, four or the like.

[0048] In one example embodiment, a value of the fifth indication equal to 0 may indicate that the bit-depth of the output picture is 8 bits, the value of the fifth indication equal to 1 may indicate that the bit-depth of the output picture is 10 bits, the value of the fifth indication equal to 2 may indicate that the bit-depth of the output picture is 12 bits, the value of the fifth indication equal to 3 may indicate that the bit-depth of the output picture is 14 bits, the value of the fifth indication equal to 4 may indicate that the bit-depth of the output picture is 16 bits. It should be understood that the above examples are described merely for purpose of description. The scope of the present disclosure is not limited in this respect.

[0049] Compared with the conventional solution where the bit-depth of the output picture is signaled using a one-bit syntax element. The proposed method can support more possible bit-depths, and thus the coding flexibility can be improved.

[0050] In some embodiments, the codestream may further comprise at least one of the following: an indication indicating a stream level to which the codestream conforms, one or more indications indicating one or more supported decoder levels provided by thecodestream, or a plurality of level indications indicating different types of restrictions and / or capabilities. In one example, a decoder level may be indicated specifically for a decoder profile and may be referred to as the level associated with a supported decoder profile provided by the codestream. By way of example rather than limitation, the indication of a decoder level may comprise an 8-bit syntax element, e.g., named decoder level idcf i ].

[0051] In some embodiments, the plurality of level indications may comprise at least one of the following: a level indication indicating a restriction on a size of the visual data, a level indication indicating a restriction on a quality or a fidelity of the visual data, a level indication indicating a restriction on a size of the codestream, or a level indication indicating a restriction on a value of a syntax element in the codestream. For example, a restriction and / or a capability indicated by one of the plurality of level indications may be allowed to be overwritten by a restriction and / or a capability indicated by a further one of the plurality of level indications.

[0052] In some embodiments, the codestream may further comprise an indication (e.g., decoder version idc or the like) indicating a decoder version that specifies a value of at least one parameter used in the conversion. By way of example, the at least one parameter may comprise a weight of the NN-based model, a bias of the NN-based model, a constant used in the conversion, and / or the like.

[0053] In some embodiments, a profile or a level may be signaled in a conditional way. In one example embodiment, the valid value range of the profile may depend on dimensions of the picture. In another example embodiment, the valid value range of the level may depend on dimensions of the picture. In a further example embodiment, the valid value range of the level may depend on the profile. In a still further example embodiment, the valid value range of the profile may depend on the level.

[0054] In some embodiments, whether to and / or how to signal a syntax element may be dependent on the profile or the level. In one example embodiment, a syntax element is signaled only if the signaled profile is a certain value or in a certain range. In a further example embodiment, a syntax element is signaled only if the signaled level is a certain value or in a certain range. In a still further example embodiment, the value range of a syntax element may depend on the signaled profile / level.

[0055] In some embodiments, information about tools may be comprised in a picture header in the codestream as a part of a substream for the picture header. In addition, a marker for a tools header (such as the above-mentioned TOH marker or the like) and an indication indicating a size of the tools header may be absent from a syntax structure for the tools header.Alternatively, the codestream may comprise a substream for a tools header, and a marker for the tools header may be specified as mandatory.

[0056] In some embodiments, a substream for a tools header may be allowed to be absent from the codestream. For example, the codestream may further comprise a sixth indication indicating whether the substream for the tools header is present in the codestream. By way of example, the sixth indication may be comprised in a picture syntax structure or a picture header syntax structure in the codestream. By way of example rather than limitation, the sixth indication equal to 1 specifies that the information about tools is explicitly signaled in the codestream, and the sixth indication equal to 0 specifies that the information about tools is not signaled in the codestream and one or more pieces of the information are inferred.

[0057] Alternatively, whether the substream for the tools header may be present in the codestream may be determined based on a condition. By way of example rather than limitation, the condition may comprise whether the next N bytes after parsing a picture header syntax structure may be equal to a value of a marker for tools header, and N may be an integer, such as 1, 2 or the like. In this case, the information about tools is signaled in the codestream only when the value of the next N bytes after parsing the picture header syntax structure is equal to the value of TOH marker. Additionally, when the information about tools is not explicitly signaled in the codestream, one or more pieces of the information may be inferred.

[0058] In some embodiments, whether information about tools is comprised in a picture header in the codestream as a part of a substream for the picture header may be dependent on a value of an indication in the codestream. In some embodiments, the codestream may be allowed to comprise a plurality of tools headers.

[0059] In some embodiments, a tools header in the codestream may comprise an index of the tools header. For example, a tools header index may be indicated in a coding unit to indicate which tools header is used for this coding unit. For example, this coding unit may be a picture header, a slice header, or the like.

[0060] In view of the above, the solutions in accordance with some embodiments of the present disclosure can advantageously improve coding efficiency and coding flexibility.

[0061] According to further embodiments of the present disclosure, a non-transitory computer-readable recording medium is provided. The non-transitory computer-readable recording medium stores a codestream of visual data which is generated by a method performed by an apparatus for visual data processing. The method comprises: performing a conversion between the visual data and the codestream with a neural network (NN)-basedmodel, wherein the codestream comprises a first indication indicating a stream profile to which the codestream conforms.

[0062] According to still further embodiments of the present disclosure, a method for storing codestream of visual data is provided. The method comprises: performing a conversion between the visual data and the codestream with a neural network (NN)-based model; and storing the codestream in a non-transitory computer-readable recording medium, wherein the codestream comprises a first indication indicating a stream profile to which the codestream conforms.

[0063] Implementations of the present disclosure can be described in view of the following clauses, the features of which can be combined in any reasonable manner.

[0064] Clause 1. A method for visual data processing, comprising: performing a conversion between visual data and a codestream of the visual data with a neural network (NN)-based model, wherein the codestream comprises a first indication indicating a stream profile to which the codestream conforms.

[0065] Clause 2. The method of clause 1, wherein the codestream further comprises one or more second indications indicating one or more supported decoder profiles provided by the codestream.

[0066] Clause 3. The method of any of clauses 1-2, wherein the codestream further comprises a third indication indicating the number of supported decoder profiles provided by the codestream.

[0067] Clause 4. The method of clause 3, wherein the one or more second indications follow the third indication in the codestream.

[0068] Clause 5. The method of any of clauses 3-4, wherein a value of the third indication plus a predetermined number is equal to the number of the supported decoder profiles provided by the codestream.

[0069] Clause 6. The method of clause 5, wherein the predetermined number is 1, and / or the number of bits used for the third indication is predetermined, and / or the third indication is represented as num decoder profiles minusl, and / or the third indication is comprised in a picture header in the codestream.

[0070] Clause 7. The method of any of clauses 2-6, wherein one of the one or more second indications that indicates the i-th supported decoder profile among the one or more supported decoder profiles is represented as decoder_profile_idc[ i ], and i is an integer, and / or the number of bits used for each of the one or more second indications is predetermined, and / or the one or more second indications are comprised in a picture header in the codestream.

[0071] Clause 8. The method of any of clauses 1-7, wherein the first indication is represented as stream profile idc, and / or the number of bits used for the first indication is predetermined, and / or the first indication is comprised in a picture header in the codestream.

[0072] Clause 9. The method of any of clauses 1-8, wherein the codestream further comprises a fourth indication indicating a level to which the codestream conforms.

[0073] Clause 10. The method of clause 9, wherein the fourth indication is represented as level idc, and / or the number of bits used for the fourth indication is predetermined, and / or the fourth indication is comprised in a picture header in the codestream.

[0074] Clause 11. The method of any of clauses 1-10, wherein the codestream further comprises a fifth indication indicating a bit-depth of an output picture of the conversion, and the number of bits used for the fifth indication is greater than one.

[0075] Clause 12. The method of clause 11, wherein the number of bits used for the fifth indication is three.

[0076] Clause 13. The method of any of clauses 11-12, wherein a value of the fifth indication equal to 0 indicates that the bit-depth of the output picture is 8 bits, and / or the value of the fifth indication equal to 1 indicates that the bit-depth of the output picture is 10 bits, and / or the value of the fifth indication equal to 2 indicates that the bit-depth of the output picture is 12 bits, and / or the value of the fifth indication equal to 3 indicates that the bit-depth of the output picture is 14 bits, and / or the value of the fifth indication equal to 4 indicates that the bit-depth of the output picture is 16 bits.

[0077] Clause 14. The method of any of clauses 1-13, wherein the codestream further comprises at least one of the following: an indication indicating a stream level to which the codestream conforms, one or more indications indicating one or more supported decoder levels provided by the codestream, or a plurality of level indications indicating different types of restrictions and / or capabilities.

[0078] Clause 15. The method of clause 14, wherein the plurality of level indications comprises at least one of the following: a level indication indicating a restriction on a size of the visual data, a level indication indicating a restriction on a quality or a fidelity of the visual data, a level indication indicating a restriction on a size of the codestream, or a level indication indicating a restriction on a value of a syntax element in the codestream.

[0079] Clause 16. The method of any of clauses 14-15, wherein a restriction and / or a capability indicated by one of the plurality of level indications is allowed to be overwritten by a restriction and / or a capability indicated by a further one of the plurality of level indications.

[0080] Clause 17. The method of any of clauses 1-16, wherein the codestream further comprises an indication indicating a decoder version that specifies a value of at least one parameter used in the conversion.

[0081] Clause 18. The method of clause 17, wherein the at least one parameter comprises at least one of the following: a weight of the NN-based model, a bias of the NN-based model, or a constant used in the conversion.

[0082] Clause 19. The method of any of clauses 1-18, wherein a profile or a level is signaled in a conditional way, or whether to and / or how to signal a syntax element is dependent on the profile or the level.

[0083] Clause 20. The method of any of clauses 1-19, wherein information about tools is comprised in a picture header in the codestream as a part of a sub stream for the picture header.

[0084] Clause 21. The method of clause 20, wherein a marker for a tools header and an indication indicating a size of the tools header is absent from a syntax structure for the tools header.

[0085] Clause 22. The method of any of clauses 1-19, wherein the codestream comprises a substream for a tools header, and a marker for the tools header is specified as mandatory.

[0086] Clause 23. The method of any of clauses 1-19, wherein a substream for a tools header is allowed to be absent from the codestream.

[0087] Clause 24. The method of clause 23, wherein the codestream further comprises a sixth indication indicating whether the substream for the tools header is present in the codestream.

[0088] Clause 25. The method of clause 24, wherein the sixth indication is comprised in a picture syntax structure or a picture header syntax structure in the codestream.

[0089] Clause 26. The method of any of clauses 24-25, wherein whether the substream for the tools header is present in the codestream is determined based on a condition.

[0090] Clause 27. The method of clause 26, wherein the condition comprises whether the next N bytes after parsing a picture header syntax structure is equal to a value of a marker for tools header, and N is an integer.

[0091] Clause 28. The method of any of clauses 1-19, wherein whether information about tools is comprised in a picture header in the codestream as a part of a substream for the picture header is dependent on a value of an indication in the codestream.

[0092] Clause 29. The method of any of clauses 1-28, wherein the codestream is allowed to comprise a plurality of tools headers.

[0093] Clause 30. The method of any of clauses 1-19, wherein a tools header in the codestream comprises an index of the tools header.

[0094] Clause 31. The method of any of clauses 1-30, wherein the visual data comprise a video, a picture of the video, or an image.

[0095] Clause 32. The method of any of clauses 1-31, wherein the conversion includes encoding the visual data into the codestream.

[0096] Clause 33. The method of any of clauses 1-31, wherein the conversion includes decoding the visual data from the codestream.

[0097] Clause 34. An apparatus for visual data processing comprising a processor and a non- transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform a method in accordance with any of clauses 1-33.

[0098] Clause 35. A non-transitory computer-readable storage medium storing instructions that cause a processor to perform a method in accordance with any of clauses 1-33.

[0099] Clause 36. A non-transitory computer-readable recording medium storing a codestream of visual data which is generated by a method performed by an apparatus for visual data processing, wherein the method comprises: performing a conversion between the visual data and the codestream with a neural network (NN)-based model, wherein the codestream comprises a first indication indicating a stream profile to which the codestream conforms.

[0100] Clause 37. A method for storing a codestream of visual data, comprising: performing a conversion between the visual data and the codestream with a neural network (NN)-based model; and storing the codestream in a non-transitory computer-readable recording medium, wherein the codestream comprises a first indication indicating a stream profile to which the codestream conforms.Example Device

[0101] Fig. 9 illustrates a block diagram of a computing device 900 in which various embodiments of the present disclosure can be implemented. The computing device 900 may be implemented as or included in the source device 110 (or the visual data encoder 114) or the destination device 120 (or the visual data decoder 124).

[0102] It would be appreciated that the computing device 900 shown in Fig. 9 is merely for purpose of illustration, without suggesting any limitation to the functions and scopes of the embodiments of the present disclosure in any manner.

[0103] As shown in Fig. 9, the computing device 900 includes a general-purpose computing device 900. The computing device 900 may at least comprise one or more processors or processing units 910, a memory 920, a storage unit 930, one or more communication units 940, one or more input devices 950, and one or more output devices 960.

[0104] In some embodiments, the computing device 900 may be implemented as any user terminal or server terminal having the computing capability. The server terminal may be a server, a large-scale computing device or the like that is provided by a service provider. The user terminal may for example be any type of mobile terminal, fixed terminal, or portable terminal, including a mobile phone, station, unit, device, multimedia computer, multimedia tablet, Internet node, communicator, desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, personal communication system (PCS) device, personal navigation device, personal digital assistant (PDA), audio / video player, digital camera / video camera, positioning device, television receiver, radio broadcast receiver, E-book device, gaming device, or any combination thereof, including the accessories and peripherals of these devices, or any combination thereof. It would be contemplated that the computing device 900 can support any type of interface to a user (such as “wearable” circuitry and the like).

[0105] The processing unit 910 may be a physical or virtual processor and can implement various processes based on programs stored in the memory 920. In a multi-processor system, multiple processing units execute computer executable instructions in parallel so as to improve the parallel processing capability of the computing device 900. The processing unit 910 may also be referred to as a central processing unit (CPU), a microprocessor, a controller or a microcontroller.

[0106] The computing device 900 typically includes various computer storage medium. Such medium can be any medium accessible by the computing device 900, including, but not limited to, volatile and non-volatile medium, or detachable and non-detachable medium. The memory 920 can be a volatile memory (for example, a register, cache, Random Access Memory (RAM)), a non-volatile memory (such as a Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), or a flash memory), or any combination thereof. The storage unit 930 may be any detachable or non-detachable medium and may include a machine-readable medium such as a memory, flash memory drive, magnetic disk or another other media, which can be used for storing information and / or visual data and can be accessed in the computing device 900.

[0107] The computing device 900 may further include additional detachable / non-detachable, volatile / non-volatile memory medium. Although not shown in Fig. 9, it is possible to provide a magnetic disk drive for reading from and / or writing into a detachable and non-volatile magnetic disk and an optical disk drive for reading from and / or writing into a detachable non-volatile optical disk. In such cases, each drive may be connected to a bus (not shown)via one or more visual data medium interfaces.

[0108] The communication unit 940 communicates with a further computing device via the communication medium. In addition, the functions of the components in the computing device 900 can be implemented by a single computing cluster or multiple computing machines that can communicate via communication connections. Therefore, the computing device 900 can operate in a networked environment using a logical connection with one or more other servers, networked personal computers (PCs) or further general network nodes.

[0109] The input device 950 may be one or more of a variety of input devices, such as a mouse, keyboard, tracking ball, voice-input device, and the like. The output device 960 may be one or more of a variety of output devices, such as a display, loudspeaker, printer, and the like. By means of the communication unit 940, the computing device 900 can further communicate with one or more external devices (not shown) such as the storage devices and display device, with one or more devices enabling the user to interact with the computing device 900, or any devices (such as a network card, a modem and the like) enabling the computing device 900 to communicate with one or more other computing devices, if required. Such communication can be performed via input / output (I / O) interfaces (not shown).

[0110] In some embodiments, instead of being integrated in a single device, some or all components of the computing device 900 may also be arranged in cloud computing architecture. In the cloud computing architecture, the components may be provided remotely and work together to implement the functionalities described in the present disclosure. In some embodiments, cloud computing provides computing, software, visual data access and storage service, which will not require end users to be aware of the physical locations or configurations of the systems or hardware providing these services. In various embodiments, the cloud computing provides the services via a wide area network (such as Internet) using suitable protocols. For example, a cloud computing provider provides applications over the wide area network, which can be accessed through a web browser or any other computing components. The software or components of the cloud computing architecture and corresponding visual data may be stored on a server at a remote position. The computing resources in the cloud computing environment may be merged or distributed at locations in a remote visual data center. Cloud computing infrastructures may provide the services through a shared visual data center, though they behave as a single access point for the users. Therefore, the cloud computing architectures may be used to provide the components and functionalities described herein from a service provider at a remote location. Alternatively, they may be provided from a conventional server or installed directly or otherwise on a clientdevice.[OHl] The computing device 900 may be used to implement visual data encoding / decoding in embodiments of the present disclosure. The memory 920 may include one or more visual data coding modules 925 having one or more program instructions. These modules are accessible and executable by the processing unit 910 to perform the functionalities of the various embodiments described herein.

[0112] In the example embodiments of performing visual data encoding, the input device 950 may receive visual data as an input 970 to be encoded. The visual data may be processed, for example, by the visual data coding module 925, to generate an encoded bitstream. The encoded bitstream may be provided via the output device 960 as an output 980.

[0113] In the example embodiments of performing visual data decoding, the input device 950 may receive an encoded bitstream as the input 970. The encoded bitstream may be processed, for example, by the visual data coding module 925, to generate decoded visual data. The decoded visual data may be provided via the output device 960 as the output 980.

[0114] While this disclosure has been particularly shown and described with references to example embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present application as defined by the appended claims. Such variations are intended to be covered by the scope of this present application. As such, the foregoing description of embodiments of the present application is not intended to be limiting.

Claims

I / We Claim:

1. A method for visual data processing, comprising: performing a conversion between visual data and a codestream of the visual data with a neural network (NN)-based model, wherein the codestream comprises a first indication indicating a stream profile to which the codestream conforms.

2. The method of claim 1, wherein the codestream further comprises one or more second indications indicating one or more supported decoder profiles provided by the codestream.

3. The method of any of claims 1-2, wherein the codestream further comprises a third indication indicating the number of supported decoder profiles provided by the codestream.

4. The method of claim 3, wherein the one or more second indications follow the third indication in the codestream.

5. The method of any of claims 3-4, wherein a value of the third indication plus a predetermined number is equal to the number of the supported decoder profiles provided by the codestream.

6. The method of claim 5, wherein the predetermined number is 1, and / or the number of bits used for the third indication is predetermined, and / or the third indication is represented as num_decoder_profiles_minusl, and / or the third indication is comprised in a picture header in the codestream.

7. The method of any of claims 2-6, wherein one of the one or more second indications that indicates the i-th supported decoder profile among the one or more supported decoder profiles is represented as decoder_profile_idc[ i ], and i is an integer, and / or the number of bits used for each of the one or more second indications is predetermined, and / or the one or more second indications are comprised in a picture header in the codestream.

8. The method of any of claims 1-7, wherein the first indication is represented as stream_profile_idc, and / orthe number of bits used for the first indication is predetermined, and / or the first indication is comprised in a picture header in the codestream.

9. The method of any of claims 1-8, wherein the codestream further comprises a fourth indication indicating a level to which the codestream conforms.

10. The method of claim 9, wherein the fourth indication is represented as level idc, and / or the number of bits used for the fourth indication is predetermined, and / or the fourth indication is comprised in a picture header in the codestream.

11. The method of any of claims 1-10, wherein the codestream further comprises a fifth indication indicating a bit-depth of an output picture of the conversion, and the number of bits used for the fifth indication is greater than one.

12. The method of claim 11, wherein the number ofbits used for the fifth indication is three.

13. The method of any of claims 11-12, wherein a value of the fifth indication equal to 0 indicates that the bit-depth of the output picture is 8 bits, and / or the value of the fifth indication equal to 1 indicates that the bit-depth of the output picture is 10 bits, and / or the value of the fifth indication equal to 2 indicates that the bit-depth of the output picture is 12 bits, and / or the value of the fifth indication equal to 3 indicates that the bit-depth of the output picture is 14 bits, and / or the value of the fifth indication equal to 4 indicates that the bit-depth of the output picture is 16 bits.

14. The method of any of claims 1-13, wherein the codestream further comprises at least one of the following: an indication indicating a stream level to which the codestream conforms, one or more indications indicating one or more supported decoder levels provided by the codestream, or a plurality of level indications indicating different types of restrictions and / or capabilities.

15. The method of claim 14, wherein the plurality of level indications comprises at least one of the following: a level indication indicating a restriction on a size of the visual data, a level indication indicating a restriction on a quality or a fidelity of the visual data, a level indication indicating a restriction on a size of the codestream, or a level indication indicating a restriction on a value of a syntax element in the codestream.

16. The method of any of claims 14-15, wherein a restriction and / or a capability indicated by one of the plurality of level indications is allowed to be overwritten by a restriction and / or a capability indicated by a further one of the plurality of level indications.

17. The method of any of claims 1-16, wherein the codestream further comprises an indication indicating a decoder version that specifies a value of at least one parameter used in the conversion.

18. The method of claim 17, wherein the at least one parameter comprises at least one of the following: a weight of the NN-based model, a bias of the NN-based model, or a constant used in the conversion.

19. The method of any of claims 1-18, wherein a profile or a level is signaled in a conditional way, or whether to and / or how to signal a syntax element is dependent on the profile or the level.

20. The method of any of claims 1-19, wherein information about tools is comprised in a picture header in the codestream as a part of a substream for the picture header.

21. The method of claim 20, wherein a marker for a tools header and an indication indicating a size of the tools header is absent from a syntax structure for the tools header.

22. The method of any of claims 1-19, wherein the codestream comprises a substream for a tools header, and a marker for the tools header is specified as mandatory.

23. The method of any of claims 1-19, wherein a substream for a tools header is allowed to be absent from the codestream.

24. The method of claim 23, wherein the codestream further comprises a sixth indication indicating whether the sub stream for the tools header is present in the codestream.

25. The method of claim 24, wherein the sixth indication is comprised in a picture syntax structure or a picture header syntax structure in the codestream.

26. The method of any of claims 24-25, wherein whether the substream for the tools header is present in the codestream is determined based on a condition.

27. The method of claim 26, wherein the condition comprises whether the next N bytes after parsing a picture header syntax structure is equal to a value of a marker for tools header, and N is an integer.

28. The method of any of claims 1-19, wherein whether information about tools is comprised in a picture header in the codestream as a part of a substream for the picture header is dependent on a value of an indication in the codestream.

29. The method of any of claims 1-28, wherein the codestream is allowed to comprise a plurality of tools headers.

30. The method of any of claims 1-19, wherein a tools header in the codestream comprises an index of the tools header.

31. The method of any of claims 1-30, wherein the visual data comprise a video, a picture of the video, or an image.

32. The method of any of claims 1-31, wherein the conversion includes encoding the visual data into the codestream.

33. The method of any of claims 1-31, wherein the conversion includes decoding the visual data from the codestream.

34. An apparatus for visual data processing comprising a processor and a non-transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform a method in accordance with any of claims 1-33.

35. A non-transitory computer-readable storage medium storing instructions that cause a processor to perform a method in accordance with any of claims 1-33.

36. A non-transitory computer-readable recording medium storing a codestream of visual data which is generated by a method performed by an apparatus for visual data processing, wherein the method comprises: performing a conversion between the visual data and the codestream with a neural network (bJN)-based model, wherein the codestream comprises a first indication indicating a stream profile to which the codestream conforms.

37. A method for storing a codestream of visual data, comprising: performing a conversion between the visual data and the codestream with a neural network (bJN)-based model; and storing the codestream in a non-transitory computer-readable recording medium, wherein the codestream comprises a first indication indicating a stream profile to which the codestream conforms.

Images