Abstract: A video coding system is provided that performs intra prediction in a mode using a neural network for block of only a set of specific block sizes. The signaling of this mode is designed to be efficient in terms of rate-distortion under this constraint. Different transformations of the context of a block and the neural network prediction of this block are introduced in order to use one single neural network for predicting blocks of several sizes, as well as the corresponding signaling. The neural network-based prediction mode considers both luminance blocks and chrominance blocks. The video coding system comprises encoder and decoder apparatuses, encoding, decoding and signal generation methods and a signal carrying information corresponding to the described coding mode.

Abstract: A coding tool set enablement scheme allows one or more coding tools to be used in the encoding or decoding of video data based on one or more characteristics related to the video. In one embodiment, some coding tools are enabled for block sizes below a particular threshold. In another embodiment, a group of coding tools are enabled based on one flag for blocks having a particular characteristic. In another embodiment, these flags are included in a bitstream with the video. In another embodiment, at least one of the flags are inferred to enable some coding tools.

Abstract: In general, encoding or decoding a picture part can involve determining a spatiotemporal motion vector predictor (STMVP) candidate for a merge mode of operation from spatial motion vector candidates taken from spatial positions around a current coding unit (CU) and a temporal motion vector candidate, where at least one embodiment involves determining the STMVP candidate based on considering at most two spatial positions and based on an average of at least two of the spatial and temporal motion vector candidates.

Abstract: In an encoding apparatus or a decoding apparatus, an encoding method or decoding method combines various coding tools with intra sub partitioning mode in which a coding unit is split in multiple sub partitions. At least one embodiment particularly aims at the selection of primary transforms among a set of multiple transforms for video encoding or decoding of intra sub block partitions. At least one embodiment particularly aims at intra coding using Ma-trix-Based Intra Prediction mode combined with Intra Sub Partition mode. At least one embodiment particularly aims at intra coding using Multi-Reference-Line intra prediction mode combined with Intra Sub Partition mode.

Abstract: Sub-block merge motion field is combined with triangle partitioning and geometric partitioning modes to further give coding and decoding schemes flexibility. In at least one embodiment, a flag is used to signal if sub-block merge candidates are used in place of regular merge candidates. In another embodiment, regular merge candidates are replaced by sub-block merge candidates. In another embodiment, at least one motion field is stored. In another embodiment, all sub-block merge candidates or only sub-block temporal motion vector predictors or only affine predictors are considered.

Abstract: Inferring an illumination compensation flag during encoding or decoding of a video image signal using frame rate up conversion can save one bit and eliminate complexity. The illumination compensation flag can be derived from the corresponding flags of at least one bi-predictive or bi-directional prediction candidates. The flag can also be derived from some function of the flags from those candidates. Alternatively, several flags can be used for respective coding or decoding of blocks if there are more than one prediction candidate using illumination compensation.

Abstract: A method for decoding a picture block is disclosed. The decoding method comprises: reconstructing reference picture from another reference picture of a decoder picture buffer of a first layer of a multi-layered stream and from data decoded from a second layer of said multi-layered stream and storing said reference picture in a decoder picture buffer of said second layer, wherein said reference picture is indicated as not to be displayed; decoding a flag indicating that a subsequently decoded picture of the second layer is not using any inter-layer prediction; and reconstructing a picture block of said subsequently decoded picture at least from said reference picture.

Abstract: Different implementations are described, particularly implementations for video encoding and decoding are presented including a method for deblocking an image. According to an implementation, in a method for deblocking an image, at least one boundary is determined between a first block of samples and a second block of samples; a boundary strength is determined according to at least one of a prediction mode of the first block and a prediction mode of the second block; and samples of the first and second blocks neighboring the at least one boundary are filtered according to the boundary strength. Advantageously, in case the prediction mode of the first block is a weighted prediction mode, the boundary strength further depends on the relative weight of samples used in predicting the first block of samples according to the weighted prediction mode of the first block and reciprocally for the second block.

Abstract: There is provided intra predicting of an image block using at least one neural network from a context comprising pixel surrounding said image block. Said intra predicting also uses an information to distinguish the missing pixels from the available pixels in the context. There are also provided encoding/decoding methods and apparatus, a device, a non-transitory computer readable medium and a computer program product.

Abstract: A method for decoding or encoding comprising: determining if an inter prediction mode called weighted prediction is enabled for a current block; and, if weighted prediction is enabled, modifying a part of a reconstruction process of said current block related to the weighted prediction and/or to at least another prediction tool of a first set of prediction tools, the first set comprising a triangle prediction mode, a geometrical prediction mode, a local illumination compensation mode, a combined intra inter prediction mode, and modes in which motion information used for motion compensation may be refined based on an optical flow model.

Abstract: An iterative training of neural networks for video coding and decoding using intra prediction is provided that finds a tradeoff between an extreme genericity and an extreme specialization to a codec for the trained neural networks. At the first iteration, the set of neural networks is trained following a partitioning approach. Then, for several iterations, the set of neural networks is inserted into the codec, and pairs of a block and its context are extracted from the partitioning of images via the codec with a single additional neural network-based mode then, the neural networks are retrained on these pairs. This way, from the second iteration, the neural networks learn an intra prediction diverging from that in the codec while still being valuable for the codec in terms of rate-distortion performance.

Abstract: Flexible methods to use a combination of coding modes while keeping good performance tradeoff are implemented with embodiments that determine coding mode information. In one embodiment, determination is made of activation of a first coding mode, and upon determination of whether a second coding mode is used, coding or decoding using the determined modes occurs. Other embodiments enable use of multiple reference lines, intra sub-block partitioning, matrix intra prediction, and low frequency non-separable transforms.

Abstract: There is provided a method for estimating weighted prediction parameters intended to be used for predicting an image block.

Abstract: A method includes encoding a first message including first parameters for a first color transform that transforms a video signal into a first color-mapped video signal; encoding a second message including second parameters for a second color transform that transforms the video signal into a second color-mapped video signal; and encoding the video signal, the first message, and the second message in a video bitstream. A method includes decoding the video bitstream into the video signal, the first message including the first parameters, and the second message including the second parameters, and performing at least one of the following: displaying the video signal; transforming the video signal into the first color-mapped video signal by applying the first color transform and displaying the first color-mapped video signal; and transforming the video signal into the second color-mapped video signal by applying the second color transform and displaying the second color-mapped video signal.

Abstract: In a video coding system, it is proposed to determine the quantization matrix based on the block area instead of the maximal value of the block size dimension (width or height). Having specific quantization matrix for each block size actually allows adaptation to image content, and thus results in better visual quality. Indeed, choosing a quantization matrix of equal-area better match the idea of “size” than choosing a quantization matrix of the maximal dimension of the rectangular block. In at least one embodiment, the quantization matrix used for video coding or decoding is selected based on a block area identifier whose value is determined as the integer value of an average of the log 2 of block width and height. Encoding and decoding methods, encoding and decoding apparatuses, non-transitory computer readable medium and computer program are described.

Abstract: Various embodiments relate to a video coding system in which some elements required for decoding are generated according to a process that not specified within the video coding system. This process is hereafter referenced to as being the “external” process. This external process may generate “external” reference pictures to be used by a decoder that is adapted to use these external pictures. Encoding method, decoding method, encoding apparatus, decoding apparatus based on this post-processing method are proposed.

Abstract: A method and apparatus to improve compression efficiency in a video compression scheme enables flexible use of local illumination compensation. Such methods comprise individual local illumination compensation for components of a video block. Such methods also comprise flexible derivation methods for illumination compensation information. In one embodiment, local illumination compensation information can be inherited from other others, such as neighboring blocks.

Abstract: Significance flags in advanced video compression systems are coded using contexts adaptive to the last N significance flags coded taken in a scanning order. One embodiment uses the last N significance flags in scanning order as a predictor to determine which of a plurality of sets of significance flag contexts to use for coding subsequent significance flags. A second embodiment uses the last N significance flags in scanning order as a predictor in order to modulate the probability value associated with significance flag contexts that are used to code significance flags for future coding.

Abstract: A method for encoding a picture block is disclosed. A predictor is determined as a weighted sum of sample values of a first motion compensated reference block in a first reference image and of a second motion compensated reference block in a second reference image. Then, a residual block determined from the picture block and the predictor is encoded in a bitstream. Advantageously, the weights of the weighted sum are determined by minimizing an error between reconstructed samples neighboring the picture block and samples neighboring the first and second reference blocks.

Abstract: Encoders and decoders of digital video signals use combined intra prediction modes for some images. In at least one embodiment, combined intra prediction modes can result from the intra prediction modes of neighboring blocks. The combined intra prediction mode can be added to a most probable modes list. Various embodiments describe techniques for combining the intra prediction modes, comprising a combination of reference samples and a combination of directions to form a prediction. Another embodiment adds a combination mode to the most probable modes list if the two modes that are combined to form it are directional modes with angle difference less than 90 degrees. Another embodiment uses a linear combination of intra prediction modes and another embodiment performs a linear combination which depends on the distance of a prediction from the left and above blocs.