EP4736432A1 - Loop filter training improvement - Google Patents

Abstract

A post-filter based on Neural Networks (NN) to replace one or several loop-filters or that can be added to the existing loop-filters, is provided. A convolutional neural network is added to, or replaces some of, the loop filters. In an embodiment, the neural network-based filter is applied to implement an Adaptive Loop Filter. A training phase generates a correction factor and scaling is implemented on the correction factor. Different filtering can be done on a per block, or per class, basis.

Description

LOOP FILTER TRAINING IMPROVEMENT

CROSS REFERENCE TO RELATED APPLICATION

This application claims the benefit of European Serial No. 23306062.3 filed June 29, 2023, which is incorporated by reference herein in its entirety.

TECHNICAL FIELD

At least one of the present embodiments generally relates to a method or an apparatus for video encoding or decoding, compression or decompression.

BACKGROUND

To achieve high compression efficiency, image and video coding schemes usually employ prediction, including motion vector prediction, and transform to leverage spatial and temporal redundancy in the video content. Generally, intra or inter prediction is used to exploit the intra or inter frame correlation, then the differences between the original image and the predicted image, often denoted as prediction errors or prediction residuals, are transformed, quantized, and entropy coded. To reconstruct the video, the compressed data are decoded by inverse processes corresponding to the entropy coding, quantization, transform, and prediction.

SUMMARY

At least one of the present embodiments generally relates to a method or an apparatus for video encoding or decoding, and more particularly, to a method or an apparatus for coding or decoding using regressive-based affine bi-prediction weights.

According to a first aspect, there is provided a method. The method comprises steps for determining a correction value from a neural network; modulating the correction value with a scaling factor; and, filtering a reconstructed portion of video by adding the reconstructed portion of video to the modulated correction value.

According to a second aspect, there is provided another method. The method comprises the aforementioned steps, implemented for encoding or decoding.

According to another aspect, there is provided an apparatus. The apparatus comprises a processor. The processor can be configured to operate on digital video data according to the aforementioned methods.

According to another aspect, there is provided an apparatus. The apparatus comprises a processor. The processor can be configured to encode a block of a video or decode video data by executing any of the aforementioned methods. According to another general aspect of at least one embodiment, there is provided a device comprising an apparatus according to any of the decoding embodiments; and at least one of (i) an antenna configured to receive a signal, the signal including the video block, (ii) a band limiter configured to limit the received signal to a band of frequencies that includes the video block, or (iii) a display configured to display an output representative of a video block.

According to another general aspect of at least one embodiment, there is provided a non-transitory computer readable medium containing data content generated according to any of the described encoding embodiments or variants.

According to another general aspect of at least one embodiment, there is provided a signal comprising video data generated according to any of the described encoding embodiments or variants.

According to another general aspect of at least one embodiment, video data or a bitstream is formatted to include data content generated according to any of the described encoding embodiments or variants.

According to another general aspect of at least one embodiment, there is provided a computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out any of the described decoding embodiments or variants.

These and other aspects, features and advantages of the general aspects will become apparent from the following detailed description of exemplary embodiments, which is to be read in connection with the accompanying drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

Figure 1 illustrates an example loop filtering process in typical video codecs.

Figure 2 illustrates an example CNN loop filter process in NNVC.

Figure 3 illustrates an example learning process.

Figure 4 illustrates an example of symmetrical filter (left) and filter rotation (right).

Figure 5 illustrates a modified model architecture used during training.

Figure 6 illustrates a model used for training with clipping.

Figure 7 illustrates a model used for training with quantization.

Figure 8 illustrates an example of ALF computation.

Figure 9 illustrates an ALF variant with clipping during the training.

Figure 10 illustrates one embodiment of a first method under the described aspects.

Figure 11 illustrates one embodiment of a second method under the described aspects.

Figure 12 illustrates one embodiment of an apparatus under the described aspects.

Figure 13 illustrates a standard, generic, video compression scheme. Figure 14 illustrates a standard, generic, video decompression scheme.

Figure 15 illustrates a processor-based system for encoding/decoding under the general described aspects.

DETAILED DESCRIPTION

The embodiments described here are in the field of video compression and generally relate to video compression and video encoding and decoding more specifically post filtering reconstructed images to reduce coding artifacts and improve the rate distortion trade-off.

To achieve high compression efficiency, image and video coding schemes usually employ block-based prediction, including motion vector prediction, and transform to leverage spatial and temporal redundancy in the video content. Generally, intra or inter prediction is used to exploit the intra or inter frame correlation, then the differences between the original block and the predicted block, often denoted as prediction errors or prediction residuals, are transformed, quantized, and entropy coded. To reconstruct the video, the compressed data are decoded by inverse processes corresponding to the entropy coding, quantization, transform, and prediction.

In the HEVC (High Efficiency Video Coding) video compression standard, motion compensated temporal prediction is employed to exploit the redundancy that exists between successive pictures of a video.

To do, a motion vector is associated to each prediction unit (Pll), which is introduced now. Each CTU (Coding Tree Unit) is represented by a Coding Tree in the compressed domain. This is a quad-tree division of the CTU, where each leaf is called a Coding Unit (CU).

Each CU is then given some Intra or Inter prediction parameters (Prediction Info). To do so, it is spatially partitioned into one or more Prediction Units (PUs), each PU being assigned some prediction information. The Intra or Inter coding mode is assigned on the CU level.

The described aspects focus on the compression of videos, particularly the (in-loop) post-filters applied to the pictures after the image or part of the image have been reconstructed. In recent video codecs, such as HEVC or VVC, there are several filters applied to the reconstructed samples of the video pictures, aiming at reducing the coding artifacts and reducing the distortion with the original picture. For instance, in HEVC, a deblocking filter (DBF) and a sample-adaptive offset (SAO) filter apply successively to the reconstructed samples. In the VVC standard another filter named adaptive loop filter (ALF) is applied at the very end of the process. During the development phase of VVC, several other supplemental block-based filters were considered: bilateral filter (BF), Hadamard filter and Diffusion filter. An example of successive loop filtering steps, corresponding to the state-of-art video codec, is depicted in Figure 1. In this example, 4 successive filters are applied: Bilateral filter, DBF, SAO and ALF. The output is the reconstructed picture samples.

These different filters are in general based on two main processes (classification and filtering) which can be decomposed as pixels classification, encoder only: determination of filter parameters (ex: DBF, SAO, ALF but not BF), filter parameters coding/decoding (ex: DBF, SAO, ALF but not BF), and class-dependent filtering.

The described aspects propose a new post-filter based on Neural Networks (NN) that may replace one or several loop-filters, or may be added to the existing loop-filters. Recently, Neural Network based filtering has been introduced, for example in NNVC (Neural Network Video Codec) in J VET AgH 11.

A convolutional NN is added to (or replaces some of) the loop filters, for example after the DBF filter.

Figure 2 shows an example of pipeline of loop filtering:

The reconstructed frame is processed by the DBF (Deblocking).

The output is used as input 1 , as well as other inputs (for example the predicted frame, residuals, the partition map, the QP map etc.).

The frame is filtered (possibly per block) and a correction is produced.

This correction is modulated by a scale factor and added to the input.

Optionally the ALF filter is applied on the result and the final frame is output.

In this process, the CNN has been learnt offline on a large dataset of blocks.

Training process

One example of a training process to learn the CNN is illustrated in Figure 3.

A large dataset of blocks is used to train the model with the inputs extracted from real encoding. Usually, the loss is computed as the MSE (Mean Square Error) or MAE (mean absolute error).

ALF

ALF Wiener Filters

In VVC, the in-loop ALF filter (adaptive loop filtering) is a linear filter whose purpose is to reduce coding artefacts on the reconstructed samples. The coefficients “c_n“of the filter are determined so that to minimize the mean square error between original samples “s(r)” and filtered samples “t(r)” by using Wiener-based adaptive filter technique. f(r) = Zn=o Cn- t(r + p_n) (eq.1) where: r=(x,y) is the sample location belongs to the to-be-filtered region “R”.

Original sample: s(r)

To-be-filtered sample: t(r)

FIR filter with N coefficients: c = [co, ... CN-I]^T

Filter tap position offset: { po, pi, ... PN-I}, where p_n denotes the sample location offset to r of the n^th filter tap. In the following, the set of tap positions is called the filter “shape”.

Filtered sample: f(r)

To find the minimum sum of squared errors (SSE) between s(r) and f(r), calculate the derivatives of SSE with respect to c_n and let the derivatives equal to zero. Then the coefficient values “c” are obtained by solving the following equation:

[Tc].c^T = v^T (eq.2) where:

In VVC, the reconstructed samples “t(r)” are classified into K classes (K=25 for luma samples, K=8 for chroma samples) and K different filters are determined with the samples of each class. The classification is made with Directionality and Activity values derived with local gradients.

In VVC, the coefficients of the ALF may be coded in the bitstream so that they can be dynamically adapted to the video content. There are also some default coefficients and the encoder indicate which set of coefficients to be used per CTU.

In VVC, symmetrical filters are used (Figure 4-left) and some filters may be obtained from other filter by rotation (Figure 4-right).

In current NNVC loop-filter (or post-filter), the training of the filters is done by directly minimizing an error between original and filtered samples, usually using a MSE (Mean Square Error) norm. However, when applying the filter, a modulation of the correction (for example a scaling) can be computed and applied (and signaled).

The same is true for traditional filters such as ALF. Moreover, in ALF 2 types of filters are used: offline trained filter and online computed filters. In both cases, the MSE between original and filtered samples is minimized.

It is proposed herein to adapt the design of the filter to take into account the scaling of the correction which can be done during the filtering stage:

For design of a model taking into account the scaling: Scaling, Scaling + bias, Scaling clipping, and Quantized scale.

For training strategy to converge to accurate filters: Multi stage training: add the scaling aware loss at the end, Batch per frame to have a unique scale.

Adaptation to ALF filtering: Fixed filter and scaling per frame, and/or Fixed filter and scaling per block.

CNN based filter training process

Scaling estimator

Assuming a NN output a correction to be added on the reconstructed frame, the filtered sample can be expressed as: y" = a * f + y'

Where y” is the filtered sample, a the scaling factor (constant for the block or a group of block, or the frame), f the correction computed by the NN and y’ the reconstructed sample.

An optimal scale is given by: a = arg min£|y" - y

Where y is the original sample, ‘i’ is the index of the sample/pixel to be filtered and |.| and a norm function (for example L2 or L1 norm). The sum is computed on all the sample of the block or a subset of blocks.

For a L2 norm, the optimal a is found by:

Figure 5 shows the modified model architecture used during training. In this case, a unique optimal scaling factor a is computed and used to modulate the correction. Note that the “div” layer is advantageously replaced by a robust division (where close to 0 denominator is replaced by a small value epsilon for numerical stability).

Scaling and bias

The same method can be applied if the filtered block is expressed as: y" = a * f + b + y'

In this case the scaling ‘a’ and offset ‘b’ are estimated using the classical linear regression.

Where N is the total number of samples in the sum and

The model is adapted the same way, by computing each term ifi , - y-) , If and combining them to compute a and b.

Robust scaling

In order to robustify the scaling, the value a is clipped, typically in the range [0.25,1.25], corresponding to the new model as shown in the figure below.

In this model, a differentiable clip layer is used to keep the gradient computation correct. Quantized scale

In practice, the scaling factor is signaled in the bitstream with an index corresponding to a set of pre-defined values. For example, the scaling factor is pick in the set {0.25, 0.5, 0.75, 1.0, 1.25}. In order to emulate this choice, the model used for training is modified accordingly.

Multi stage training

In order to stabilize the training, the scaling of the CNN output is not added from the beginning of the training. Typically, the model is first trained for N1 epochs with a fixed scaling of 1. Then the scaling part is added and the model is refined for subsequent N2 epochs. Taking into account the change of norm during the training, the whole process can be sum up as the table below.

Other training strategy, for example first switching the norm can also be used.

Batch composition

During inference of the CNN, the scaling factor can be set constant for a set of blocks. In order to take this into account, the training strategy is adapted.

For each batch of samples, all samples inside a batch are taken from the same frame. The scaling factor a is then computed for the whole batch and applied for all samples of the batch. In another embodiment, the scaling factor is computed per sample of the batch (ie per block of pixel samples) and applied independently for each sample of the block.

Adaptation to ALF filter

The adaptation to ALF filter consists in signaling at least one scaling factor in the bitstream.

Fixed filters with low number of classes

When the number of classes (or filters) is low, a scaling factor can be associated with each class (or filter), then signalled. This is for example the case for VTM or in ECM for the signalled filter mode.

Rescaling per filter

In current ALF process, a set of offline learned filters is used to filter the blocks.

In VTM, an offline-learned (known at encoder and decoder) filterset can be used instead an online-learned filterset. A filterset contains up to 25 filters, together with the mapping between each class (the results of the classifier) and its corresponding filter. For each CTU, the sample corresponding to the class is then filtered using this filter.

In order to improve the flexibility of the filtering, it is proposed to add a scaling factor on the result of the correction given by the filter, similarly to what was done in NN filtering: y" = a * f + y'

Where y” is the final filtered result, a the scaling factor, f the correction (y=z-y’, where z is the output of ALF), y’ the reconstructed frame (after other loop-filter, typically the output of SAO).

Scaling factor choice

In a variant, at encoder a RDO loop is performed on both the filterset and the scaling factor associated with each filter. In the APS, associated with each filter, a scaling factor, for example among 4 values {0.25, 0.5, 1 , 1.25} is signalled. In another variant, at encoder a RDO loop is performed on both the class and the scaling factor. In the APS, associated with each class, a scaling factor, for example among 4 values {0.25, 0.5, 1 , 1.25} is signalled. In this case, a filter used by several classes can have several scaling factor.

In a variant, a code is associated with each scaling factor to minimize the coding cost, for example:

Slice rescaling

Another variant is to add a unique scaling factor for all filtered samples correction: all correction (ie. f=z-y’) are rescaled with a unique scale factor, whatever the class or the filter.

The scaling factor can for example be signaled in the APS or the slice header.

Scaling factor choice

In a variant, at encoder a RDO loop is performed on both the filter choices and a set of scaling factor.

In a variant, the optimal scaling factor is computed for each filter choices and the scaling factor the closest to the one in the finite set of scaling factor is transmitted.

CTU based scaling factor

In a variant, the scaling factor is signaled for each CTU (or block of pixel for which the same class is used). The signaling of the scaling factor advantageously uses an entropy coding of the index of the scaling factor in the scaling factor set. In a variant, a conditional entropy is used by using a context on the index of scaling factor the top and/or left CTU of the current CTU.

Fixed filters computation

In order to improve the performance of the fixed filters used by the ALF process, the fixed filters are learnt using the same method as the one described for the NN filter model (Figure 8):

For a set of samples of a given class (optionally further split per QP or other features).

The distortion between filtered samples and original is minimized. A scaling factor is computed on the correction and applied before the distortion.

In a variant, the convolutional filters are learned under the constraint that they are normalized, that is:

Zn=o c„ = l (eq.3)

In another variant, the convolutional filters are learned without any constraint.

In a variant, the full ALF pipeline, including the clipping of the difference with the central value y’O. The clipping is done for each difference before the convolution with the filter (conv). As before, an optimal quantized and clipped value a is computed for each sample in the patch (for example corresponding to a CTU). In a variant, the value is computed for a set of patches (of the same frame).

One embodiment of a method 1000 under the general aspects described here is shown in Figure 10. The method commences at start block 1001 and control proceeds to block 1010 for determining a correction value from a neural network. Control proceeds from block 1010 to block 1020 for modulating the correction value with a scaling factor. Control proceeds from block 1020 to block 1030 for filtering a reconstructed portion of video by adding the reconstructed portion of video to the modulated correction value.

One embodiment of a method 1100 under the general aspects described here is shown in Figure 11. The method commences at start block 1101 and control proceeds to block 1110 for determining a correction factor from a neural network and determining a scaling factor from signaling. Control proceeds from block 1110 to block 1120 for performing filtering of a reconstructed portion of video during encoding or decoding.

Figure 12 shows one embodiment of an apparatus 1200 for encoding, decoding, compressing or decompressing, or filtering of video data using the aforementioned methods. The apparatus comprises Processor 1210 and can be interconnected to a memory 1220 through at least one port. Both Processor 1210 and memory 1220 can also have one or more additional interconnections to external connections.

Processor 1210 is also configured to either insert or receive information in a bitstream and, either compressing, encoding, or decoding using any of the described aspects.

The embodiments described here include a variety of aspects, including tools, features, embodiments, models, approaches, etc. Many of these aspects are described with specificity and, at least to show the individual characteristics, are often described in a manner that may sound limiting. However, this is for purposes of clarity in description, and does not limit the application or scope of those aspects. Indeed, all of the different aspects can be combined and interchanged to provide further aspects. Moreover, the aspects can be combined and interchanged with aspects described in earlier filings as well.

The aspects described and contemplated in this application can be implemented in many different forms. Figures 13, 14, and 15 provide some embodiments, but other embodiments are contemplated and the discussion of Figures 13, 14, and 15 does not limit the breadth of the implementations. At least one of the aspects generally relates to video encoding and decoding, and at least one other aspect generally relates to transmitting a bitstream generated or encoded. These and other aspects can be implemented as a method, an apparatus, a computer readable storage medium having stored thereon instructions for encoding or decoding video data according to any of the methods described, and/or a computer readable storage medium having stored thereon a bitstream generated according to any of the methods described.

In the present application, the terms “reconstructed” and “decoded” may be used interchangeably, the terms “pixel” and “sample” may be used interchangeably, the terms “image,” “picture” and “frame” may be used interchangeably. Usually, but not necessarily, the term “reconstructed” is used at the encoder side while “decoded” is used at the decoder side.

Various methods are described herein, and each of the methods comprises one or more steps or actions for achieving the described method. Unless a specific order of steps or actions is required for proper operation of the method, the order and/or use of specific steps and/or actions may be modified or combined.

Various methods and other aspects described in this application can be used to modify modules, for example, the intra prediction, entropy coding, and/or decoding modules (160, 260, 145, 230), of a video encoder 100 and decoder 200 as shown in Figure 13 and Figure 14. Moreover, the present aspects are not limited to VVC or HEVC, and can be applied, for example, to other standards and recommendations, whether pre-existing or future-developed, and extensions of any such standards and recommendations (including VVC and HEVC). Unless indicated otherwise, or technically precluded, the aspects described in this application can be used individually or in combination.

Various numeric values are used in the present application. The specific values are for example purposes and the aspects described are not limited to these specific values.

Figure 13 illustrates an encoder 100. Variations of this encoder 100 are contemplated, but the encoder 100 is described below for purposes of clarity without describing all expected variations.

Before being encoded, the video sequence may go through pre-encoding processing (101), for example, applying a color transform to the input color picture (e.g., conversion from RGB 4:4:4 to YCbCr 4:2:0), or performing a remapping of the input picture components in order to get a signal distribution more resilient to compression (for instance using a histogram equalization of one of the color components). Metadata can be associated with the preprocessing and attached to the bitstream.

In the encoder 100, a picture is encoded by the encoder elements as described below. The picture to be encoded is partitioned (102) and processed in units of, for example, CUs. Each unit is encoded using, for example, either an intra or inter mode. When a unit is encoded in an intra mode, it performs intra prediction (160). In an inter mode, motion estimation (175) and compensation (170) are performed. The encoder decides (105) which one of the intra mode or inter mode to use for encoding the unit, and indicates the intra/inter decision by, for example, a prediction mode flag. Prediction residuals are calculated, for example, by subtracting (110) the predicted block from the original image block.

The prediction residuals are then transformed (125) and quantized (130). The quantized transform coefficients, as well as motion vectors and other syntax elements, are entropy coded (145) to output a bitstream. The encoder can skip the transform and apply quantization directly to the non-transformed residual signal. The encoder can bypass both transform and quantization, i.e., the residual is coded directly without the application of the transform or quantization processes.

The encoder decodes an encoded block to provide a reference for further predictions. The quantized transform coefficients are de-quantized (140) and inverse transformed (150) to decode prediction residuals. Combining (155) the decoded prediction residuals and the predicted block, an image block is reconstructed. In-loop filters (165) are applied to the reconstructed picture to perform, for example, deblocking/SAO (Sample Adaptive Offset) filtering to reduce encoding artifacts. The filtered image is stored at a reference picture buffer (180).

Figure 14 illustrates a block diagram of a video decoder 200. In the decoder 200, a bitstream is decoded by the decoder elements as described below. Video decoder 200 generally performs a decoding pass reciprocal to the encoding pass as described in Figure 13. The encoder 100 also generally performs video decoding as part of encoding video data.

In particular, the input of the decoder includes a video bitstream, which can be generated by video encoder 100. The bitstream is first entropy decoded (230) to obtain transform coefficients, motion vectors, and other coded information. The picture partition information indicates how the picture is partitioned. The decoder may therefore divide (235) the picture according to the decoded picture partitioning information. The transform coefficients are de-quantized (240) and inverse transformed (250) to decode the prediction residuals. Combining (255) the decoded prediction residuals and the predicted block, an image block is reconstructed. The predicted block can be obtained (270) from intra prediction (260) or motion-compensated prediction (i.e., inter prediction) (275). In-loop filters (265) are applied to the reconstructed image. The filtered image is stored at a reference picture buffer (280).

The decoded picture can further go through post-decoding processing (285), for example, an inverse color transform (e.g. conversion from YcbCr 4:2:0 to RGB 4:4:4) or an inverse remapping performing the inverse of the remapping process performed in the pre- encoding processing (101). The post-decoding processing can use metadata derived in the pre-encoding processing and signaled in the bitstream.

Figure 15 illustrates a block diagram of an example of a system in which various aspects and embodiments are implemented. System 1000 can be embodied as a device including the various components described below and is configured to perform one or more of the aspects described in this document. Examples of such devices include, but are not limited to, various electronic devices such as personal computers, laptop computers, smartphones, tablet computers, digital multimedia set top boxes, digital television receivers, personal video recording systems, connected home appliances, and servers. Elements of system 1000, singly or in combination, can be embodied in a single integrated circuit (IC), multiple ICs, and/or discrete components. For example, in at least one embodiment, the processing and encoder/decoder elements of system 1000 are distributed across multiple ICs and/or discrete components. In various embodiments, the system 1000 is communicatively coupled to one or more other systems, or other electronic devices, via, for example, a communications bus or through dedicated input and/or output ports. In various embodiments, the system 1000 is configured to implement one or more of the aspects described in this document.

The system 1000 includes at least one processor 1010 configured to execute instructions loaded therein for implementing, for example, the various aspects described in this document. Processor 1010 can include embedded memory, input output interface, and various other circuitries as known in the art. The system 1000 includes at least one memory 1020 (e.g., a volatile memory device, and/or a non-volatile memory device). System 1000 includes a storage device 1040, which can include non-volatile memory and/or volatile memory, including, but not limited to, Electrically Erasable Programmable Read-Only Memory (EEPROM), Read-Only Memory (ROM), Programmable Read-Only Memory (PROM), Random Access Memory (RAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), flash, magnetic disk drive, and/or optical disk drive. The storage device 1040 can include an internal storage device, an attached storage device (including detachable and non-detachable storage devices), and/or a network accessible storage device, as non-limiting examples.

System 1000 includes an encoder/decoder module 1030 configured, for example, to process data to provide an encoded video or decoded video, and the encoder/decoder module 1030 can include its own processor and memory. The encoder/decoder module 1030 represents module(s) that can be included in a device to perform the encoding and/or decoding functions. As is known, a device can include one or both of the encoding and decoding modules. Additionally, encoder/decoder module 1030 can be implemented as a separate element of system 1000 or can be incorporated within processor 1010 as a combination of hardware and software as known to those skilled in the art.

Program code to be loaded onto processor 1010 or encoder/decoder 1030 to perform the various aspects described in this document can be stored in storage device 1040 and subsequently loaded onto memory 1020 for execution by processor 1010. In accordance with various embodiments, one or more of processor 1010, memory 1020, storage device 1040, and encoder/decoder module 1030 can store one or more of various items during the performance of the processes described in this document. Such stored items can include, but are not limited to, the input video, the decoded video or portions of the decoded video, the bitstream, matrices, variables, and intermediate or final results from the processing of equations, formulas, operations, and operational logic.

In some embodiments, memory inside of the processor 1010 and/or the encoder/decoder module 1030 is used to store instructions and to provide working memory for processing that is needed during encoding or decoding. In other embodiments, however, a memory external to the processing device (for example, the processing device can be either the processor 1010 or the encoder/decoder module 1030) is used for one or more of these functions. The external memory can be the memory 1020 and/or the storage device 1040, for example, a dynamic volatile memory and/or a non-volatile flash memory. In several embodiments, an external non-volatile flash memory is used to store the operating system of, for example, a television. In at least one embodiment, a fast external dynamic volatile memory such as a RAM is used as working memory for video coding and decoding operations, such as for MPEG-2 (MPEG refers to the Moving Picture Experts Group, MPEG-2 is also referred to as ISO/IEC 13818, and 13818-1 is also known as H.222, and 13818-2 is also known as H.262), HEVC (HEVC refers to High Efficiency Video Coding, also known as H.265 and MPEG-H Part 2), or VVC (Versatile Video Coding, a new standard being developed by JVET, the Joint Video Experts Team).

The input to the elements of system 1000 can be provided through various input devices as indicated in block 1130. Such input devices include, but are not limited to, (i) a radio frequency (RF) portion that receives an RF signal transmitted, for example, over the air by a broadcaster, (ii) a Component (COMP) input terminal (or a set of COMP input terminals), (iii) a Universal Serial Bus (USB) input terminal, and/or (iv) a High Definition Multimedia Interface (HDMI) input terminal. Other examples, not shown in Figure 15, include composite video.

In various embodiments, the input devices of block 1130 have associated respective input processing elements as known in the art. For example, the RF portion can be associated with elements suitable for (i) selecting a desired frequency (also referred to as selecting a signal, or band-limiting a signal to a band of frequencies), (ii) downconverting the selected signal, (iii) band-limiting again to a narrower band of frequencies to select (for example) a signal frequency band which can be referred to as a channel in certain embodiments, (iv) demodulating the downconverted and band-limited signal, (v) performing error correction, and (vi) demultiplexing to select the desired stream of data packets. The RF portion of various embodiments includes one or more elements to perform these functions, for example, frequency selectors, signal selectors, band-limiters, channel selectors, filters, downconverters, demodulators, error correctors, and demultiplexers. The RF portion can include a tuner that performs various of these functions, including, for example, downconverting the received signal to a lower frequency (for example, an intermediate frequency or a near-baseband frequency) or to baseband. In one set-top box embodiment, the RF portion and its associated input processing element receives an RF signal transmitted over a wired (for example, cable) medium, and performs frequency selection by filtering, downconverting, and filtering again to a desired frequency band. Various embodiments rearrange the order of the above-described (and other) elements, remove some of these elements, and/or add other elements performing similar or different functions. Adding elements can include inserting elements in between existing elements, such as, for example, inserting amplifiers and an analog-to-digital converter. In various embodiments, the RF portion includes an antenna.

Additionally, the USB and/or HDMI terminals can include respective interface processors for connecting system 1000 to other electronic devices across USB and/or HDMI connections. It is to be understood that various aspects of input processing, for example, Reed-Solomon error correction, can be implemented, for example, within a separate input processing IC or within processor 1010 as necessary. Similarly, aspects of USB or HDMI interface processing can be implemented within separate interface les or within processor 1010 as necessary. The demodulated, error corrected, and demultiplexed stream is provided to various processing elements, including, for example, processor 1010, and encoder/decoder 1030 operating in combination with the memory and storage elements to process the datastream as necessary for presentation on an output device.

Various elements of system 1000 can be provided within an integrated housing, Within the integrated housing, the various elements can be interconnected and transmit data therebetween using suitable connection arrangement, for example, an internal bus as known in the art, including the Inter-IC (I2C) bus, wiring, and printed circuit boards.

The system 1000 includes communication interface 1050 that enables communication with other devices via communication channel 1060. The communication interface 1050 can include, but is not limited to, a transceiver configured to transmit and to receive data over communication channel 1060. The communication interface 1050 can include, but is not limited to, a modem or network card and the communication channel 1060 can be implemented, for example, within a wired and/or a wireless medium.

Data is streamed, or otherwise provided, to the system 1000, in various embodiments, using a wireless network such as a Wi-Fi network, for example IEEE 802.11 (IEEE refers to the Institute of Electrical and Electronics Engineers). The Wi-Fi signal of these embodiments is received over the communications channel 1060 and the communications interface 1050 which are adapted for Wi-Fi communications. The communications channel 1060 of these embodiments is typically connected to an access point or router that provides access to external networks including the Internet for allowing streaming applications and other over- the-top communications. Other embodiments provide streamed data to the system 1000 using a set-top box that delivers the data over the HDMI connection of the input block 1130. Still other embodiments provide streamed data to the system 1000 using the RF connection of the input block 1130. As indicated above, various embodiments provide data in a non- streaming manner. Additionally, various embodiments use wireless networks other than Wi-Fi, for example a cellular network or a Bluetooth network.

The system 1000 can provide an output signal to various output devices, including a display 1100, speakers 1110, and other peripheral devices 1120. The display 1100 of various embodiments includes one or more of, for example, a touchscreen display, an organic lightemitting diode (OLED) display, a curved display, and/or a foldable display. The display 1100 can be for a television, a tablet, a laptop, a cell phone (mobile phone), or another device. The display 1100 can also be integrated with other components (for example, as in a smart phone), or separate (for example, an external monitor for a laptop). The other peripheral devices 1120 include, in various examples of embodiments, one or more of a stand-alone digital video disc (or digital versatile disc) (DVR, for both terms), a disk player, a stereo system, and/or a lighting system. Various embodiments use one or more peripheral devices 1120 that provide a function based on the output of the system 1000. For example, a disk player performs the function of playing the output of the system 1000.

In various embodiments, control signals are communicated between the system 1000 and the display 1100, speakers 1110, or other peripheral devices 1120 using signaling such as AV. Link, Consumer Electronics Control (CEC), or other communications protocols that enable device-to-device control with or without user intervention. The output devices can be communicatively coupled to system 1000 via dedicated connections through respective interfaces 1070, 1080, and 1090. Alternatively, the output devices can be connected to system 1000 using the communications channel 1060 via the communications interface 1050. The display 1100 and speakers 1110 can be integrated in a single unit with the other components of system 1000 in an electronic device such as, for example, a television. In various embodiments, the display interface 1070 includes a display driver, such as, for example, a timing controller (T Con) chip.

The display 1100 and speaker 1110 can alternatively be separate from one or more of the other components, for example, if the RF portion of input 1130 is part of a separate set- top box. In various embodiments in which the display 1100 and speakers 1110 are external components, the output signal can be provided via dedicated output connections, including, for example, HDMI ports, USB ports, or COMP outputs.

The embodiments can be carried out by computer software implemented by the processor 1010 or by hardware, or by a combination of hardware and software. As a nonlimiting example, the embodiments can be implemented by one or more integrated circuits. The memory 1020 can be of any type appropriate to the technical environment and can be implemented using any appropriate data storage technology, such as optical memory devices, magnetic memory devices, semiconductor-based memory devices, fixed memory, and removable memory, as non-limiting examples. The processor 1010 can be of any type appropriate to the technical environment, and can encompass one or more of microprocessors, general purpose computers, special purpose computers, and processors based on a multi-core architecture, as non-limiting examples.

Various implementations involve decoding. “Decoding”, as used in this application, can encompass all or part of the processes performed, for example, on a received encoded sequence to produce a final output suitable for display. In various embodiments, such processes include one or more of the processes typically performed by a decoder, for example, entropy decoding, inverse quantization, inverse transformation, and differential decoding. In various embodiments, such processes also, or alternatively, include processes performed by a decoder of various implementations described in this application.

As further examples, in one embodiment “decoding” refers only to entropy decoding, in another embodiment “decoding” refers only to differential decoding, and in another embodiment “decoding” refers to a combination of entropy decoding and differential decoding. Whether the phrase “decoding process” is intended to refer specifically to a subset of operations or generally to the broader decoding process will be clear based on the context of the specific descriptions and is believed to be well understood by those skilled in the art.

Various implementations involve encoding. In an analogous way to the above discussion about “decoding”, “encoding” as used in this application can encompass all or part of the processes performed, for example, on an input video sequence to produce an encoded bitstream. In various embodiments, such processes include one or more of the processes typically performed by an encoder, for example, partitioning, differential encoding, transformation, quantization, and entropy encoding. In various embodiments, such processes also, or alternatively, include processes performed by an encoder of various implementations described in this application.

As further examples, in one embodiment “encoding” refers only to entropy encoding, in another embodiment “encoding” refers only to differential encoding, and in another embodiment “encoding” refers to a combination of differential encoding and entropy encoding. Whether the phrase “encoding process” is intended to refer specifically to a subset of operations or generally to the broader encoding process will be clear based on the context of the specific descriptions and is believed to be well understood by those skilled in the art.

Note that the syntax elements as used herein are descriptive terms. As such, they do not preclude the use of other syntax element names.

When a figure is presented as a flow diagram, it should be understood that it also provides a block diagram of a corresponding apparatus. Similarly, when a figure is presented as a block diagram, it should be understood that it also provides a flow diagram of a corresponding method/process.

Various embodiments may refer to parametric models or rate distortion optimization. In particular, during the encoding process, the balance or trade-off between the rate and distortion is usually considered, often given the constraints of computational complexity. It can be measured through a Rate Distortion Optimization (RDO) metric, or through Least Mean Square (LMS), Mean of Absolute Errors (MAE), or other such measurements. Rate distortion optimization is usually formulated as minimizing a rate distortion function, which is a weighted sum of the rate and of the distortion. There are different approaches to solve the rate distortion optimization problem. For example, the approaches may be based on an extensive testing of all encoding options, including all considered modes or coding parameters values, with a complete evaluation of their coding cost and related distortion of the reconstructed signal after coding and decoding. Faster approaches may also be used, to save encoding complexity, in particular with computation of an approximated distortion based on the prediction or the prediction residual signal, not the reconstructed one. Mix of these two approaches can also be used, such as by using an approximated distortion for only some of the possible encoding options, and a complete distortion for other encoding options. Other approaches only evaluate a subset of the possible encoding options. More generally, many approaches employ any of a variety of techniques to perform the optimization, but the optimization is not necessarily a complete evaluation of both the coding cost and related distortion.

The implementations and aspects described herein can be implemented in, for example, a method or a process, an apparatus, a software program, a data stream, or a signal. Even if only discussed in the context of a single form of implementation (for example, discussed only as a method), the implementation of features discussed can also be implemented in other forms (for example, an apparatus or program). An apparatus can be implemented in, for example, appropriate hardware, software, and firmware. The methods can be implemented in, for example, a processor, which refers to processing devices in general, including, for example, a computer, a microprocessor, an integrated circuit, or a programmable logic device. Processors also include communication devices, such as, for example, computers, cell phones, portable/personal digital assistants (“PDAs”), and other devices that facilitate communication of information between end-users.

Reference to “one embodiment” or “an embodiment” or “one implementation” or “an implementation”, as well as other variations thereof, means that a particular feature, structure, characteristic, and so forth described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of the phrase “in one embodiment” or “in an embodiment” or “in one implementation” or “in an implementation”, as well any other variations, appearing in various places throughout this application are not necessarily all referring to the same embodiment.

Additionally, this application may refer to “determining” various pieces of information. Determining the information can include one or more of, for example, estimating the information, calculating the information, predicting the information, or retrieving the information from memory.

Further, this application may refer to “accessing” various pieces of information. Accessing the information can include one or more of, for example, receiving the information, retrieving the information (for example, from memory), storing the information, moving the information, copying the information, calculating the information, determining the information, predicting the information, or estimating the information.

Additionally, this application may refer to “receiving” various pieces of information. Receiving is, as with “accessing”, intended to be a broad term. Receiving the information can include one or more of, for example, accessing the information, or retrieving the information (for example, from memory). Further, “receiving” is typically involved, in one way or another, during operations such as, for example, storing the information, processing the information, transmitting the information, moving the information, copying the information, erasing the information, calculating the information, determining the information, predicting the information, or estimating the information.

It is to be appreciated that the use of any of the following 7”, “and/or”, and “at least one of”, for example, in the cases of “A/B”, “A and/or B” and “at least one of A and B”, is intended to encompass the selection of the first listed option (A) only, or the selection of the second listed option (B) only, or the selection of both options (A and B). As a further example, in the cases of “A, B, and/or C” and “at least one of A, B, and C”, such phrasing is intended to encompass the selection of the first listed option (A) only, or the selection of the second listed option (B) only, or the selection of the third listed option (C) only, or the selection of the first and the second listed options (A and B) only, or the selection of the first and third listed options (A and C) only, or the selection of the second and third listed options (B and C) only, or the selection of all three options (A and B and C). This may be extended, as is clear to one of ordinary skill in this and related arts, for as many items as are listed.

Also, as used herein, the word “signal” refers to, among other things, indicating something to a corresponding decoder. For example, in certain embodiments the encoder signals a particular one of a plurality of transforms, coding modes or flags. In this way, in an embodiment the same transform, parameter, or mode is used at both the encoder side and the decoder side. Thus, for example, an encoder can transmit (explicit signaling) a particular parameter to the decoder so that the decoder can use the same particular parameter. Conversely, if the decoder already has the particular parameter as well as others, then signaling can be used without transmitting (implicit signaling) to simply allow the decoder to know and select the particular parameter. By avoiding transmission of any actual functions, a bit savings is realized in various embodiments. It is to be appreciated that signaling can be accomplished in a variety of ways. For example, one or more syntax elements, flags, and so forth are used to signal information to a corresponding decoder in various embodiments. While the preceding relates to the verb form of the word “signal”, the word “signal” can also be used herein as a noun.

As will be evident to one of ordinary skill in the art, implementations can produce a variety of signals formatted to carry information that can be, for example, stored or transmitted. The information can include, for example, instructions for performing a method, or data produced by one of the described implementations. For example, a signal can be formatted to carry the bitstream of a described embodiment. Such a signal can be formatted, for example, as an electromagnetic wave (for example, using a radio frequency portion of spectrum) or as a baseband signal. The formatting can include, for example, encoding a data stream and modulating a carrier with the encoded data stream. The information that the signal carries can be, for example, analog or digital information. The signal can be transmitted over a variety of different wired or wireless links, as is known. The signal can be stored on a processor-readable medium.

The preceding sections describe a number of embodiments, across various claim categories and types. Features of these embodiments can be provided alone or in any combination. Further, embodiments can include one or more of the following features, devices, or aspects, alone or in any combination, across various claim categories and types:

At least one embodiment comprises implementing a filtering operation using a neural network to determine a correction factor.

At least one embodiment comprises encoding or decoding a video block by using filtering in a reconstructed video path according to the described embodiments.

At least one embodiment comprises the above embodiment to implement an Adaptive Loop Filter.

At least one embodiment further comprises determining of a correction factor based on minimizing a distance between reconstructed samples and original samples of a portion of video. At least one embodiment further comprises the above embodiments wherein a clipping or rounding operation is performed before applying a scaling factor.

At least one embodiment further comprises the above embodiments wherein the scaling factor is signaled for each block of pixels.

At least one embodiment comprises the above embodiments wherein a value of the scaling factor is associated with a class of filter that is implemented.

At least one embodiment comprises any encoding or decoding operation based on the above operations.

At least one embodiment comprises performing encoding or decoding with the aforementioned methods on a sub-block.

At least one embodiment comprises a bitstream or signal that includes one or more of the described syntax elements, or variations thereof.

At least one embodiment comprises a bitstream or signal that includes syntax conveying information generated according to any of the embodiments described.

At least one embodiment comprises creating and/or transmitting and/or receiving and/or decoding according to any of the embodiments described.

At least one embodiment comprises a method, process, apparatus, medium storing instructions, medium storing data, or signal according to any of the embodiments described.

At least one embodiment comprises inserting in the signaling syntax elements that enable the decoder to determine decoding information in a manner corresponding to that used by an encoder.

At least one embodiment comprises creating and/or transmitting and/or receiving and/or decoding a bitstream or signal that includes one or more of the described syntax elements, or variations thereof.

At least one embodiment comprises a TV, set-top box, cell phone, tablet, or other electronic device that performs transform method(s) according to any of the embodiments described.

At least one embodiment comprises a TV, set-top box, cell phone, tablet, or other electronic device that performs transform method(s) determination according to any of the embodiments described, and that displays (e.g., using a monitor, screen, or other type of display) a resulting image.

At least one embodiment comprises a TV, set-top box, cell phone, tablet, or other electronic device that selects, bandlimits, or tunes (e.g., using a tuner) a channel to receive a signal including an encoded image, and performs transform method(s) according to any of the embodiments described. At least one embodiment comprises a TV, set-top box, cell phone, tablet, or other electronic device that receives (e.g., using an antenna) a signal over the air that includes an encoded image, and performs transform method(s).

Claims

1. A method, comprising: determining a correction value from a neural network; modulating the correction value with a scaling factor; and, filtering a reconstructed portion of video by adding the reconstructed portion of video to the modulated correction value.

2. An apparatus, comprising: a memory, and a processor, configured to: determine a correction value from a neural network; modulate the correction value with a scaling factor; and, filter a reconstructed portion of video by adding the reconstructed portion of video to the modulated correction value.

3. The method of Claim 1 or the apparatus of Claim 2, wherein the scaling factor is signaled from an encoder to a corresponding decoder.

4. The method of any one of Claims 1 or 3, or the apparatus of any one of Claims 2 or 3, wherein an offset is added to the sum of the reconstructed portion of video and the modulated correction value.

5. The method of any one of Claims 1, 3, or 4, or the apparatus of any one of Claims 2, 3, or 4, wherein training of the neural network is performed initially with a fixed scaling and subsequently refined.

6. The method of any one of Claims 1, 3, 4, or 5, or the apparatus of any one of Claims 2, 3, 4, or 5, wherein said filtering is performed as an adaptive loop filter.

7. The method of any one of Claims 1, 3, 4, 5, or 6, or the apparatus of any one of Claims 2, 3, 4, 5, or 6, wherein a value of the scaling factor is associated with a class of filter that is implemented.

8. The method of any one of Claims 1 , 3, 4, 5, 6, or 7, or the apparatus of any one of Claims 2, 3, 4, 5, 6, or 7, wherein a code is signaled indicative of the scaling factor.

9. The method of any one of Claims 1 , 3, 4, 5, 6, 7, or 8, or the apparatus of any one of Claims 2, 3, 4, 5, 6, 7, or 8, wherein the scaling factor is signaled for each block of pixels.

10. The method of any one of Claims 1 , 3, 4, 5, 6, 7, 8, or 9, or the apparatus of any one of Claims 2, 3, 4, 5, 6, 7, 8, or 9, wherein the scaling factor is computed on the correction value and applied before determining a minimization of distortion between filtered samples and an original signal.

11 . The method of any one of Claims 1 , 3, 4, 5, 6, 7, 8, 9, or 10, or the apparatus of any one of Claims 2, 3, 4, 5, 6, 7, 8, 9, or 10, wherein a clipping or rounding operation is performed before applying a scaling factor.

12. A device comprising: an apparatus according to Claim 2; and at least one of (i) an antenna configured to receive a signal, the signal including the video block, (ii) a band limiter configured to limit the received signal to a band of frequencies that includes the video block, and (iii) a display configured to display an output representative of a video block.

13. A non-transitory computer readable medium containing data content generated according to the method of any one of claims 1 , or 3 through 11 , or by the apparatus of any one of claims 2, or 3 through 11 , for playback using a processor.

14. A signal comprising video data generated according to the method of any one of claims 1 , or 3 through 11 , or by the apparatus of any one of claims 2, or 3 through 11 , for playback using a processor.

15. A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method of any one of claims 1 , or 3 through 11.