公开(公告)号：WO2021126769A1

公开(公告)日：2021-06-24

申请号：PCT/US2020/064862

申请日：2020-12-14

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： GALPIN, Franck ,  RACAPE, Fabien ,  BEGAINT, Jean ,  DUMAS, Thierry

IPC: H04N19/90 ,  H04N19/176 ,  G06N3/04 ,  G06N3/0454

Abstract: In one implementation, a picture is partitioned into multiple blocks, with uniform or different block sizes. Each block is compressed by an auto-encoder, which may comprise a deep neural network and entropy encoder. The compressed block may be reconstructed or decoded with another deep neural network. Quantization may be used in the encoder side, and de-quantization at the decoder side. When the block is encoded, neighboring blocks may be used as causal information. Latent information can also be used as input to a layer at the encoder or decoder. Vertical and horizontal position information can further be used to encode and decode the image block. A secondary network can be applied to the position information before it is used as input to a layer of the neural network at the encoder or decoder. To reduce blocking artifact, the block may be extended before being input to the encoder.

公开(公告)号：WO2020131659A3

公开(公告)日：2020-06-25

申请号：PCT/US2019/066448

申请日：2019-12-16

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： LELEANNEC, Fabrice ,  GALPIN, Franck ,  FRANCOIS, Edouard

IPC: H04N19/52

Abstract: The general aspects extend motion modes, such as merge with motion vector difference, and symmetrical motion vector difference, to motion models beyond a simple translational model, for example in combination with merge and alternative temporal motion vector prediction modes. Embodiments extend the use of MMVD and SMVD motion vector coding tools to all the motion model derivation methods and temporal prediction methods that are supported in proposed video standards, so as to increase the overall compression performance. Particular embodiments describe combining MMVD or SMVD with the affine motion model, the ATMVP motion model, the planar motion model, the regressive motion field, the triangle-partition-based motion model, the GBI temporal prediction method, the LIC temporal prediction method and the Multi-hypothesis prediction method.

公开(公告)号：WO2020072401A1

公开(公告)日：2020-04-09

申请号：PCT/US2019/053933

申请日：2019-10-01

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： ROBERT, Antoine ,  LELEANNEC, Fabrice ,  GALPIN, Franck

IPC: H04N19/503

Abstract: At least a method and an apparatus are presented for efficiently encoding or decoding video. For example, for a block being encoded, a set of predictor candidates is determined. For a current potential predictor candidate in a set of potential predictor candidates, it is determined that the current potential predictor candidate is different from any predictor candidate in a subset of predictor candidates from the set of predictor candidates and in response the current potential predictor candidate is added to the set of predictor candidates. Thus, the set of predictor candidates is pruned with partial comparison in the set. The block is encoded or decoded based on a predictor candidate from pruned set of predictor candidates.

公开(公告)号：WO2020056095A1

公开(公告)日：2020-03-19

申请号：PCT/US2019/050755

申请日：2019-09-12

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： GALPIN, Franck ,  ROBERT, Antoine ,  LELEANNEC, Fabrice

IPC: H04N19/52 ,  H04N19/139 ,  H04N19/105

Abstract: Methods and apparatus for creating additional affine candidates. Virtual and temporal candidates are determined using neighboring spatial and temporal sub-blocks. The sub-blocks are examined in an order known to both an encoder and a decoder. Valid sub-blocks are used to compute an affine model. The candidates can be filtered and added to a candidate list conditionally based on various criteria. The candidates can be used to determine control point motion vectors and a motion flow field can be determined. Motion vectors for sub-blocks within a video coding block can be determined. Motion compensation can be performed using the improved affine candidates and encoding/decoding based on the improved affine motion compensation.

公开(公告)号：WO2020005572A1

公开(公告)日：2020-01-02

申请号：PCT/US2019/037150

申请日：2019-06-14

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： ROBERT, Antoine ,  GALPIN, Franck ,  POIRIER, Tangi

IPC: H04N19/52 ,  H04N19/426 ,  H04N19/54 ,  H04N19/513

Abstract: A video encoder or decoder processes portions of video using virtual temporal affine motion candidates. Under the general aspects, virtual temporal affine candidates are created using only the classical temporal motion buffer information, avoiding the storage of additional affine parameters in a temporal motion buffer. A motion field for encoding or decoding a video block is generated based on the virtual temporal affine candidates. In one embodiment, collocated motion candidates are rescaled by adjusting the picture order count of the determined motion field. In another embodiment, resolution adaptation is performed to enable a current motion buffer to correspond to a reference motion buffer.

公开(公告)号：WO2019217095A1

公开(公告)日：2019-11-14

申请号：PCT/US2019/029305

申请日：2019-04-26

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： ROBERT, Antoine ,  LELEANNEC, Fabrice ,  GALPIN, Franck

IPC: H04N19/176 ,  H04N19/513 ,  H04N19/577

Abstract: A video encoder or decoder processes portions of video with less delay when its processes are parallelized and avoids delays caused by dependence on the completion of prior processes. In one embodiment, a motion vector predictor from a neighboring block of video is used in a subsequent later block of video before it is finished being refined for use in the neighboring block. In another embodiment, information from a neighboring block is confined to include blocks in the same coding tree unit. In another embodiment, a motion vector predictor is checked to see whether it is already in a list of candidates before adding it to the list to expedite the process.

公开(公告)号：WO2019212661A1

公开(公告)日：2019-11-07

申请号：PCT/US2019/024229

申请日：2019-03-27

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： RACAPE, Fabien ,  GALPIN, Franck ,  ROBERT, Antoine

IPC: H04N19/126 ,  H04N19/182 ,  H04N19/167 ,  H04N19/597

Abstract: A method and an apparatus for coding an omnidirectional video and corresponding method and apparatus for decoding an omnidirectional video are disclosed. According to the present disclosure, for at least one block of a picture of said omnidirectional video, a value of each pixel of said block is scaled (32) according to a spatial position of the pixel in said picture, and said block is encoded (33), wherein said scaling is different for at least 2 pixels within said block.

公开(公告)号：WO2019156757A1

公开(公告)日：2019-08-15

申请号：PCT/US2019/012269

申请日：2019-01-04

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： GALPIN, Franck ,  RACAPE, Fabien ,  DE LAGRANGE, Philippe

IPC: H04N19/117 ,  H04N19/157 ,  H04N19/176 ,  H04N19/82

CPC classification number: H04N19/117 ,  H04N19/157 ,  H04N19/176 ,  H04N19/82

Abstract: A method for decoding a picture block is disclosed. To this aim, a picture part is decoded (S220). Then, the decoded block is first filtered (S230) with a deblocking filter. At least one sample of the decoded block is classified (S240) into one current class of N classes of an adaptive loop filter, N being an integer. Finally, the sample of the decoded block is filtered (S250) with an adaptive loop filter associated with the current class. Advantageously, the filtering with an adaptive loop filter is weighted responsive to the current class and further to information derived from the filtering with a deblocking filter.

公开(公告)号：WO2019118539A1

公开(公告)日：2019-06-20

申请号：PCT/US2018/065079

申请日：2018-12-12

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： LELEANNEC, Fabrice ,  GALPIN, Franck ,  JAISWAL, Sunil ,  RACAPE, Fabien

IPC: H04N19/176 ,  H04N19/119 ,  G06T9/00 ,  H04N19/96

Abstract: 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.

公开(公告)号：WO2019071001A1

公开(公告)日：2019-04-11

申请号：PCT/US2018/054402

申请日：2018-10-04

Applicant: INTERDIGITAL VC HOLDINGS, INC

Inventor： GALPIN, Franck ,  RACAPE, Fabien ,  BORDES, Philippe

IPC: H04N19/51 ,  H04N19/105 ,  H04N19/139 ,  H04N19/176

Abstract: Different implementations are described for determining one or more illumination compensation parameters for a current block being encoded by a video encoder or decoded by a video decoder, based on the selection of one or more neighboring samples. The selection of the one or more neighboring samples is based on information used to reconstruct a plurality of neighboring reconstructed blocks. The selection may be based on the motion information, such as motion vector and reference picture information. In one example, only samples from neighboring reconstructed blocks that have (1) the same reference picture index and/or (2) a motion vector close to the motion vector of the current block is selected. In another example, if the current block derives or inherits some motion information from a top or left neighboring block, then only the top or left neighboring samples are selected for IC parameter calculation.