Interdigital Ce Patent Holdings

Interdigital Ce Patent Holdings, Sas

Thomson Licensing

Neus Sabater

Matthieu Hog

Valter Drazic

Guillaume Boisson

Christine Guillemot

Mozhdeh Seifi

Benoit Vandame

Julien Fleureau

Bertrand Chupeau

Jurgen Stauder

Cedric Thebault

Julia Navarro

Didier Doyen

Franck Thudor

Renaud Dore

Thierry Tapie

Vincent Demoulin

Erik Reinhard

Francois Le Clerc

Olivier Bureller

Philippe Schmouker

Gerard Briand

Frederic Babon

Remy Gendrot

Elena Garces

Gustavo Luiz Sandri

Juergen Stauder

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.

Method and apparatus for generating compact multiplane images

Methods and devices for encoding and decoding 3D scenes of an immersive video are disclosed with the related data stream. Taking advantage of the fact that parts of the 3D scene does not change from one frame of the video to another, even when the cameras move and/or the lighting condition change, dynamic and static parts of the 3D scene are encoded in different atlases. In an embodiment, static patch atlases are repeated between two updates. In another embodiment, only updates are encoded and transmitted. The decoder maintains a memory associating entity of the 3D scene with a set of static patches that is updated with instructions linked to update static patch atlases. At each presentation time the static part of the 3D scene to decode is obtained from the memory.

Volumetric video with long-term patch entity memory

An apparatus and method for processing a light field comprising a plurality of views of a 3D scene includes obtaining a super-ray representation for the light field, wherein the super-ray representation comprises a plurality of super-rays, wherein each super-ray groups pixels corresponding to a set of light rays having a similar color from each of the plurality of views, and wherein the set of light rays for each super-ray originates from one area of the 3D scene; and processing the light field by processing the super-ray representation for the light field, wherein processing the light field comprises at least one of editing the light field, segmenting the light field, and refocusing the light field.

Method for processing a light field image delivering a super-rays representation of a light field image

Methods and devices for generating a multiplane image from a representation of a 3D scene are disclosed. Given a representation of the 3D scene, for example as a multiview image, a first MPI is generated by a convolutional neural network trained for generating a MPI according to a provided sampling of the depths of the 3D scene. The presence of objects in different layers, that is the complementary of the accumulated transparency of layers, is analyzed to resample the sampling of layers' depth. The new sampling is used by the CNN to generate a new MPI from a representation of the same 3D scene.

Method and apparatus for generating adaptive multiplane images

A method and an apparatus for data retrieval in a lightfield database are described. An acquiring unit of the apparatus acquires a sample data. An operation unit determines a plurality of two-dimensional (2D) images from each 4D lightfield data of the lightfield database, and match the sample data with the determined 2D images according to geometrical parameters of the sample data and geometrical parameters of the 2D images. One of the 2D images is selected as a target image based on the matching result, and the 4D lightfield from which the target image is determined is retrieved.

Method and apparatus for data retrieval in a lightfield database

The present disclosure concerns a method for processing a light field image comprising a set of image views. The method is remarkable in that it comprises:

A device comprising filtering means having a pattern of at least four blocks wherein a second block is located vertical to a first block, a third block is located horizontal to said first block and a fourth block is located vertical to said third block and horizontal to said second block; and means to generate a new image from images captured using said filtered rays.

Filter array for demosaicing

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&#x3c;N&#x2264;M, a process comprising: &#x2014;determining depth maps for the images in the set of N images delivering a set of N depth maps; &#x2014;for at least one current pixel for which a depth has not yet been estimated: &#x2014;deciding if a candidate depth corresponding to a depth value in the set of N depth maps is consistent or not with the other depth map(s) of the set of N depth maps; &#x2014;selecting the candidate depth as being the estimated depth for the current pixel if the candidate depth is decided as consistent. The process is enforced iteratively with a new N value which is lower than the previous N value used in the previous iteration of the process.

Method for estimating a depth for pixels, corresponding device and computer program product

A method and device for processing a light field video is described. The light field video includes a set of image views per unit of time, the light field video being associated with a scene without cuts. In the method a first super-rays representation of reference image views at a given time is determined based on centroids. A second super-rays representation associated with corresponding views of a subsequent set of image views is next determined based on de-projection and re-projection of centroids. The displacement of centroids between the first and second super-rays is determined and then the determined displacement is applied to centroids of the second super-rays representation.

Method for processing a light field video based on the use of a super-rays representation

The present disclosure concerns a method for processing a light field image comprising a set of image views. The method is remarkable in that it comprises: selecting () a set of pixels, named centroids, within a given image view in said light field image, each centroid being associated with a unique label and a unique light ray; de-projecting said centroids, that delivers a set of points in a 3D space; re-projecting said points of said set of points in a 3D space in at least one other image view in said light field image, which is different from said reference view, that delivers a set of re-projected centroids; and determining (), for each pixel, being associated with a light ray, within a neighborhood of a re-projected centroid, a label related to one of the centroids, said determining relying on a proximity criterion in term of color between pixels and centroids, and a proximity criterion in term of spatial distances between pixels and re-projected centroids; and updating (), for a given centroid, a color value associated with said given centroid, and spatial coordinates of said given centroid within said given image view, wherein said updating comprises: de-projecting pixels in said at least one other image view that are associated with a same label of said given centroid, delivering a set of obtained points; and re-projecting said obtained points into said given image view, delivering a set of projected points; and averaging both color values associated with said projected points and spatial coordinates associated with said projected points for defining updated information related to said given centroid.

A method for rendering an image, called a final image, from at least one image acquired by a camera array, is provided. According to such a method, the determination of a color value for at least one pixel of the final image, called a current pixel, comprises:

Method for rendering a final image from initial images acquired by a camera array, corresponding device, computer program product and computer-readable carrier medium

The disclosure concerns a method for filtering spurious pixels in a depth-map. It is important to filter a depth-map to remove the spurious pixels. One issue when filtering spurious pixels, is to remove them while preserving the boundaries of the real details of the depth-map. A known approach to filter spurious pixels is to use a bi-lateral filter. However, the bi-lateral filter is not efficient to remove the spurious pixels. The proposed solution enables to remove spurious pixels in a depth-map while preserving the sharp edges of the depth-map and smoothing faint details or noise.

Method for filtering spurious pixels in a depth-map

Selecting at least one surface in a light field, such as a light field associated with multiple views corresponding to different view points of a same scene, may include displaying one of the multiple views as a reference view, selecting at least one surface in the reference view, identifying a set of pixels belonging to the selected surface, which are occluded in the reference view but visible in at least one of the multiple views, projecting the set of pixels into the reference view on the basis of a value of the pixels of the set in the view or views in which they are visible in order to form an upgraded reference view, displaying the upgraded reference view, and updating the selected surface in the upgraded reference view.

Method and apparatus for selecting a surface in a light field, and corresponding computer program product

In one embodiment, it is proposed a method for obtaining at least one sub-aperture image being associated with one view, from raw light field data corresponding to recorded data by an array of pixels sensors positioned behind an array of micro-lenses in a light field camera, each of said pixel sensor recording a linear mixing of up to four different views. The method is remarkable in that it comprises applying a signal separation process on said raw data by using an inverse of a mixing matrix A, said mixing matrix comprising coefficients that convey weighting information of said up to four different views recorded by a pixel sensor.

Growing community of inventors

Betton, France

Neus Sabater