公开(公告)号：US12155808B2

公开(公告)日：2024-11-26

申请号：US17642084

申请日：2020-09-10

Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS

Inventor： Bertrand Chupeau ,  Tomas Volker ,  Guillaume Boisson

IPC: H04N13/111 ,  G06T3/40 ,  G06T7/90 ,  G06V10/44 ,  G06V10/56

Abstract: The present disclosure relates to method and apparatus for the estimation of an accurate multiplane image from a set of posed images. The accuracy of an MPI representation is measured by the performance of the views generated by it through inverse homography sampling and alpha compositing. A variable number of posed images at a possibly different resolution representative of scenes with arbitrary geometry are used as input of the system. A first level of three modules, possibly trained based on deep learning methods, is built for extracting view and scene features and color scores. Numerous levels of the same three modules may be built and organized in a structure where a level deals with down-scaled version of the posed images.

公开(公告)号：US12073579B2

公开(公告)日：2024-08-27

申请号：US18008843

申请日：2021-06-07

Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS

Inventor： Guillaume Boisson ,  Tomas Volker ,  Bertrand Chupeau ,  Didier Doyen

IPC: G06T7/557 ,  G06T7/80 ,  H04N23/957

CPC classification number: G06T7/557 ,  G06T7/80 ,  H04N23/957 ,  G06T2207/10024 ,  G06T2207/20021 ,  G06T2207/20084 ,  G06T2207/30244

Abstract: An apparatus and a method are provided for image processing. In one embodiment, the method comprises accessing a plurality of images captured by at least a reference camera, wherein the images represent a plurality of views corresponding to said same scene. A plurality of plane sweep volume (PSV) slices are then generated from said images and computing for each slice a flow map from at least the reference camera calibration parameter and this flow map a previous slice of the plane sweep volume is generated.

公开(公告)号：US20240244259A1

公开(公告)日：2024-07-18

申请号：US18289464

申请日：2022-05-06

Applicant: InterDigital CE Patent Holdings, SAS

Inventor： Didier Doyen ,  Valter Drazic ,  Vincent Brac De La Perriere ,  Guillaume Boisson

IPC: H04N19/597 ,  G03H1/08 ,  H04N13/00 ,  H04N13/388 ,  H04N19/176

CPC classification number: H04N19/597 ,  G03H1/08 ,  H04N13/388 ,  H04N19/176 ,  H04N2013/0081

Abstract: Methods and apparatuses for encoding/decoding data content representative of a volumetric video are provided, wherein. the encoding/decoding comprises encoding in/decoding from a bitstream. an indicator specifying whether data content has information representative of at least one set of depth layers. the information representative of a set of depth layers specifying a number of depth layers and a depth value for each of the depth layers for a layer-based representation of the volumetric video. Methods and apparatuses for reconstructing Computer Generated Holograms from a reconstructed layered-based representation of the volumetric video are also provided.

公开(公告)号：US12184992B2

公开(公告)日：2024-12-31

申请号：US17798678

申请日：2021-02-18

Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS

Inventor： Frederic Babon ,  Guillaume Boisson ,  Tristan Langlois

IPC: H04N23/951 ,  H04N5/265 ,  H04N23/90

Abstract: A method and system are provided for generating an image from each camera array in a camera array matrix. In one embodiment, the method comprises increasing redundancy between to be captured images from the camera matrix by rotating direction of any cameras disposed in upper and lower rows of said matrix by a 90 degree angle around the roll axis. Then any cameras disposed at the corners of the matrix are rotated in an angle that is less than 90 degrees around the roll axis. Subsequently, the location of central cameras are determined and analysed so that they can be rotated and disposed in a manner that provides both horizontal and vertical compensation for any redundancies.

公开(公告)号：US20240196011A1

公开(公告)日：2024-06-13

申请号：US18285798

申请日：2022-03-29

Applicant: InterDigital CE Patent Holdings, SAS

Inventor： Valter Drazic ,  Didier Doyen ,  Guillaume Boisson ,  Valerie Allie ,  Vincent Brac De La Perriere

IPC: H04N19/597 ,  H04N19/119 ,  H04N19/184 ,  H04N19/30

CPC classification number: H04N19/597 ,  H04N19/119 ,  H04N19/184 ,  H04N19/30

Abstract: Methods (1400) and apparatuses for encoding/decoding a sequence of multiple plane images representative of a 3D scene are provided, wherein the sequence of multiple plane images comprises at least one multiple plane image. a multiple plane image comprising a plurality of layers. said encoding comprising encoding in a bitstream. for at least one layer of the plurality of layers of the at least one multiple plane image. an indicator indicating whether the at least one layer has changed with respect to a corresponding layer of a reference multiple plane image, and encoding the at least one multiple plane image. Methods (1100) and apparatuses for reconstructing Computer Generated Holograms from the sequence of multiple plane images are also provided.

公开(公告)号：US20240098235A1

公开(公告)日：2024-03-21

申请号：US18272472

申请日：2022-01-11

Applicant: InterDigital CE Patent Holdings, SAS

Inventor： Neus Sabater ,  Julia Navarro ,  Julien Fleureau ,  Guillaume Boisson

IPC: H04N13/161 ,  H04N13/139 ,  H04N13/156 ,  H04N13/194

CPC classification number: H04N13/161 ,  H04N13/139 ,  H04N13/156 ,  H04N13/194 ,  H04N2013/0081

Abstract: Methods and devices for generated multiplane images from a representation of a 3D scene are disclosed. When an MPI is generated by the system, an image of the accumulation of the alpha values is computed. A convolutional networked is trained with a penalization function that penalizes MPIs with high values of accumulated alpha according to a parameter selected or trained to reduce the redundancy of information between layers of the MPI. When generating a MPI from a subset of the views of a new captured 3D scene, a first MPI is generated with the trained CNN with the associated parameter. An error is calculated between the other views and corresponding synthesized with the first MPI. This error is used to modify the parameter. Then, a second MPI is generated with the trained CNN with the new parameter.

公开(公告)号：US20250106428A1

公开(公告)日：2025-03-27

申请号：US18850870

申请日：2023-03-24

Applicant: InterDigital CE Patent Holdings, SAS

Inventor： Franck Galpin ,  Philippe Bordes ,  Guillaume Boisson ,  Tangi Poirier

IPC: H04N19/51 ,  H04N19/176

Abstract: A method and an apparatus for encoding or decoding a video are provided. At least one motion compensation interpolation filter for a block of the video is determined. In an embodiment, the length of the motion compensation interpolation filter is adapted based on block conditions. A prediction block is determined based on the at least one motion compensation interpolation filter and a reference block determined for the block and the block of the video is encoded or decoded based at least on the prediction block.

公开(公告)号：US11962745B2

公开(公告)日：2024-04-16

申请号：US17763757

申请日：2020-09-29

Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS

Inventor： Didier Doyen ,  Franck Galpin ,  Guillaume Boisson

IPC: H04N13/178 ,  G06T7/593 ,  H04N13/194 ,  H04N13/243 ,  H04N13/271 ,  H04N13/282 ,  H04N19/513 ,  H04N19/597 ,  H04N19/70

CPC classification number: H04N13/178 ,  G06T7/596 ,  H04N13/194 ,  H04N13/243 ,  H04N13/271 ,  H04N13/282 ,  H04N19/513 ,  H04N19/597 ,  H04N19/70

Abstract: A method and system are provided for processing image content. The method comprises receiving information about a content image captured at least by one camera. The content includes multi-view representation of an image including both distorted and undistorted areas. The camera parameters and image parameters are then obtained and used to determine to which areas are undistorted and which areas are distorted in said image. This is used to calculate depth map of the image using the determined undistorted and distorted information. A final stereoscopic image is then rendered that uses the distorted and undistorted areas and calculation of depth map.

公开(公告)号：US11257236B2

公开(公告)日：2022-02-22

申请号：US17261375

申请日：2019-07-17

Applicant: InterDigital CE Patent Holdings, SAS

Inventor： Frederic Babon ,  Neus Sabater ,  Matthieu Hog ,  Didier Doyen ,  Guillaume Boisson

IPC: G06T7/557

Abstract: A method is proposed for estimating a depth for pixels in a matrix of M images. Such method comprises, at least for one set of N images among the M images, 2