Interdigital Vc Holdings, Inc.

Interdigital Madison Patent Holdings, Sas

Thomson Licensing

Interdigital Ce Patent Holdings, Sas

Fabien Racape

Franck Galpin

Philippe Bordes

Fabrice Urban

Gagan Bihari Rath

Tangi Poirier

Fabrice Leleannec

Edouard Francois

Gagan Rath

Fabrice Le Leannec

Dominique Thoreau

Jerome Vieron

Antoine Robert

Ya Chen

Sunil Jaiswal

Benoit Vandame

Thierry Viellard

Jean Begaint

Guillaume Boisson

Karam Naser

Fabrice LeLeannec

Paul Kerbiriou

Christine Guillemot

Aurelie Martin

Shahab Hamidi-Rad

Fatma Hawary

Marie Babel

Jean-Jacques Fuchs

Fabrice Le Léannec

Hyomin Choi

Syed Mateen Ul Haq

Juan Merlos

Simon Lefort

Olivier Deforges

Swayambhoo Jain

Methods and apparatuses for video coding and decoding are provided. The method of video encoding includes determining a set of parameters for illumination compensation associated with a first motion compensated reference block of a block in a picture of a video based on a function of a set of samples of the first motion compensated reference block and a set of samples of a second motion compensated reference block of the block, processing a prediction of the block based on the set of parameters, the prediction being associated with the first motion compensated reference block and encoding the block based on the processed prediction. A bitstream formatted to include encoded data, a computer-readable storage medium and a computer program product are also described.

Method and apparatus for video encoding and decoding based on illumination compensation

Systems, methods, and instrumentalities are disclosed herein for range-based channel removal and frame packing for compressing feature tensors with video codecs. In examples, the encoder may determine whether a channel is active or inactive. The encoder may perform channel reduction based on the determination that the channel is inactive. A feature tensor may be encoded based on the reduced channel. In examples, the decoder may obtain a channel activation indication associated with a channel. Based on the channel activation indication associated with the channel, the decoder may determine whether the channel is active or inactive. A feature tensor may be decoded based on the determination of whether the channel is active or inactive.

Range-based channel removal and frame packing for compressing feature tensors with video codecs

Encoding or decoding video information can involve, for example, partitioning a coding unit of the video information using a partitioning based on a modification of a constraint on partitioning that is associated with a pipeline configuration for reconstruction of the coding unit, where the modification is based on an information dependency between two or more pipeline units associated with the pipeline configuration, and encoding or decoding the video information based on the partitioning.

Virtual pipeline for video encoding and decoding

Described are video coding systems comprising a post-processing stage using position dependent intra prediction combination where a predicted sample is modified based on a weighting between a value of a left or top reference sample and the obtained predicted value for the sample, wherein the left or top reference sample is determined based on the intra prediction angle. This provides better computing efficiency while keeping identical compression performance. Encoding method, decoding method, encoding apparatus and decoding apparatus based on this post-processing stage are proposed.

Method and device for picture encoding and decoding using position dependent intra prediction combination

A block of video data is split using one or more of several possible partition operations by using the partitioning choices obtained through use of a deep learning-based image partitioning. In at least one embodiment, the block is split in one or more splitting operations using a convolutional neural network. In another embodiment, inputs to the convolutional neural network come from pixels along the block's causal borders. In another embodiment, boundary information, such as the location of partitions in spatially neighboring blocks, is used by the convolutional neural network. Methods, apparatus, and signal embodiments are provided for encoding.

Deep learning based image partitioning for video compression

A video encoder or decoder processes portions of video using intra coding and with variable block shapes. Under the general aspects, intra prediction directions are adapted to the block shape or aspect ratio. The general aspects described adaptively replace several conventional angular intra prediction modes with wide-angle intra prediction modes for non-square blocks. The total number of angular directions for any block can remain the same as in prior video coding standards or can be reduced or expanded. To keep the same number of prediction directions, directions along a shorter rectangular edge of a target block are removed but replaced with addition directions along the longer edge of the rectangular target block. For directions with wide angles, reference sample smoothing is performed. Signaling can be provided to inform a corresponding decoder regarding the prediction modes and directions.

Block shape adaptive intra prediction directions for quadtree-binary tree

Decoding or encoding picture information can involve determining a value associated with a prediction of a pixel of a block of picture information, wherein, the prediction is based on an intra-prediction along a non-diagonal direction, determining, from among a plurality of decoded pixels neighboring the block on the top and the left, at least four reference samples for the block based on the non-diagonal direction, and wherein the determining of the value comprises an interpolation based on a quadratic model and the four reference samples; and decoding or encoding at least a portion of the picture information based on the value.

Intra prediction for video encoding and decoding

Video signal coding and decoding functions can generate lists of potential candidates to use in coding and decoding, for example, predictors. Video signal coding component candidate undergo operations before potential inclusion in candidate lists. The candidates are checked after being modified by the operations to see if other equal candidates are already in the candidate list. If equal candidates are not in the list, the modified candidates are added to the candidate list. If equal candidates are already in the list, the modified candidates are not added to the list. Operations that can be performed comprise rounding and clipping.

Method and apparatus for candidate list pruning

Different implementations are described, particularly implementations for video encoding and decoding based on linear weighted intra prediction, also called matrix based intra prediction, are presented. Accordingly, for a block being encoded or decoded in linear weighted intra prediction, obtaining intra predicted samples from at least two matrix-vector products between at least two selected weight matrices of reduced size and a set of neighboring reference samples. Advantageously, such arrangement allows to reduce the amount of memory for storing data and to reduce the complexity of the intra prediction samples computation.

Method and apparatus for video encoding and decoding with matrix based intra-prediction

A method includes decoding a first portion of video data consisting of an information set consisting of information representative of a plurality of candidate sets of sample adaptive offset filter parameters. A set of sample adaptive offset parameters comprises information representative of an offset to be added to a sample value of a current block. A first syntax element representing an index that identifies a first candidate set of the plurality of candidate sets of sample adaptive offset filter parameters is decoded from the video data for the current block. The current block is decoded from a second portion of the video data different from the first portion. The decoded current block is filtered with the first candidate set identified by the index. The first portion is signaled with syntax elements at a level of a block of a group of blocks comprising the current block decoded first in decoding order.

Method and a device for picture encoding and decoding

A method and apparatus for performing intra prediction for encoding or decoding adds multiple prediction modes to those of prior intra prediction schemes. A horizontal mode, a vertical mode, and a diagonal mode are added. Reference pixels for each of the added modes can come from multiple pixel positions away from a block to be encoded or decoded. Reference pixels to the left and above a block are reconstructed from those already coded. Reference pixels from right of, and below, a block are estimated or extrapolated and can be based on other pixels around the block. An index can be sent in a bitstream indicating which prediction was used.

Intra prediction mode extension

A block of video data is split using one or more of several possible partition operations by using the partitioning choices obtained through use of a texture-based image partitioning. In at least one embodiment, the block is split in one or more splitting operations using a convolutional neural network. In another embodiment, inputs to the convolutional neural network come from pixels along the block's causal borders. In another embodiment, boundary information, such as the location of partitions in spatially neighboring blocks, is used by the texture analysis. Methods, apparatus, and signal embodiments are provided for encoding.

Texture-based partitioning decisions for video compression

A method for video decoding is disclosed. A directional intra prediction mode is decoded for a block of a picture, the directional intra prediction mode having a direction. Based on the directional intra prediction mode, a first predictor and a second predictor for a sample in the current block are accessed, the first and second predictors being on a line at least approximating the direction. A sample value of the sample is predicted by interpolation using the first and second predictors, responsive to a difference between the second and first predictors, wherein the difference is scaled by at least a ratio that is based on a location of the sample in the block, and wherein a denominator of the ratio is a power of two regardless of the location of the sample. The sample of the block is reconstructed based on the predicted sample value.

Method and apparatus for low-complexity bi-directional intra prediction in video encoding and decoding

Methods and apparatus for using wide-angle intra prediction for rectangular blocks enable greater prediction angles. Wide-angle intra prediction enables intra prediction direction angles beyond the conventional 45 and −135 degrees. In one embodiment, when a video block to be coded or decoded is non-square, additional intra prediction directions are enabled in the direction of the longer block edge and more reference samples are available along that edge. An index is used to indicate the prediction direction and can be adapted according to the additional intra predictions in the longer direction, with correspondingly fewer prediction directions along the shorter block edge. This preserves the number of prediction modes that need to be indexed but allows their angles to correspond to the shape of the block.

Directions for wide angle intra prediction

A method for video decoding is disclosed. A first reconstructed version of an image block of an encoded video is accessed. The first reconstructed version of said image block is filtered by a first neural network to form a second reconstructed version of said image block to be used as reference. The second reconstructed version of said image block is filtered by a second neural network to form a third reconstructed version of said image block to be displayed. The first and second neural networks are trained jointly.

Growing community of inventors

Palo Alto, CA, United States of America

Fabien Racape