Abstract: Methods, devices and stream are disclosed for encoding, transporting and decoding a 3D scene prepared to be viewed from the inside of a viewing zone. A central view comprising texture and depth information is encoded by projected points of the 3D scene visible from a central point of view onto an image plane. Patches are generated to encode small parts of the 3D scene not visible from the central point of view. At the rendering, a viewport image is generated for the current point of view. Holes, that is dis-occluded areas, of the viewport are filled using a patch based inpainting algorithm adapted to take the patches, warped according to the rotation and translation between virtual camera used for capturing the patch and the current virtual camera.

Abstract: A method for encoding a volumetric video content representative of a 3D scene is disclosed. The method comprises obtaining a reference viewing box and an intermediate viewing box defined within the 3D scene. For the reference viewing bounding box, the volumetric video reference subcontent is encoded as a central image and peripheral patches for parallax. For the intermediate viewing bounding box, the volumetric video intermediate sub-content is encoded as intermediate central patches which are differences between the intermediate central image and the reference central image.

Abstract: Methods, devices and video data encoding a volumetric 3D scene are disclosed. The user is allowed to modify values of rendering effects for some objects of the 3D scene in ranges provided by the content creator or the broadcaster. Metadata describing the possibilities of modifications, the concerned objects and authorized ranges of values are associated with the payload content. On the decoding side, according to these metadata an interface is provided to the user for modifying the values in the authorized ranges.

Abstract: A method and a device for generating a data stream representative of a volumetric video generated from a sequence of multi-plane images are disclosed. A quantization law depending on an angular resolution used to generate patches from the multi-plane images is set up. For each intra-periods of the frame sequence, patches are generated for a given angular resolution. If generated patches do not fit in atlas images of a target size, the angular resolution is decreased and patches are generated again according to this new angular resolution.

Abstract: Methods, apparatus and data stream are described to encode, transmit and decode an atlas-based representation of a 3D scene based on a multiplane image (MPI) representation in which a depth component is encoded in each layer. Layers of the MPI are clustered on a transparency basis to generate texture, transparency and depth patch pictures. Patch pictures are packed in at least one atlas image. Metadata associating each patch to a layer and each layer to a depth and a depth quantization law are encoded in the data stream with the at least one atlas. At the decoding side, the MPI with a depth component is retrieved from the data stream and is used to render a viewport image from a viewpoint in the neighborhood of the center of the MPI.

Abstract: Methods and devices are provided to encode and decode a data stream carrying data representative of a three-dimensional scene, the data stream comprising color pictures packed in a color image; depth pictures packed in a depth image; and a set of patch data items comprising de-projection data; data for retrieving a color picture in the color image and geometry data. These data are inserted in the video track of the stream with associated temporal information. The color and depth pictures that are repeated at least two times in a sequence of patches are not packed in the images but inserted in the image track of the stream and are pointed by color or geometry data.

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.

Abstract: Methods and apparatus for encoding and decoding a volumetric scene are disclosed. A set of attribute and geometry patches is obtained by projecting samples of the volumetric scene onto the patches according to projection parameters. If the geometry patch is comparable to a planar layer located at a constant depth according to the projection parameters, only the attribute patch is packed in an attribute atlas image and the depth value is encoded in metadata. Otherwise, both attribute and geometry patches are packed in an atlas. At the decoding, if metadata for an attribute patch indicates that its geometry may be determined from the projection parameters and a constant depth, the attributes are inverse projected on a planar layer. Otherwise, attributes are inverse projected according to the associated geometry patch.

Abstract: Methods, devices and stream are disclosed to encode and decode a scene (such as a point cloud) in the context of a patch-based transmission of a volumetric video content. Attributes of points of the scene are projected onto patches. Every point has a geometry attribute. For other attributes, like transparency of displacement attribute, some points may have no value. According to the present principles, each attribute is encoded in a different atlas with its own layout. This allow to save pixel rate in memory of the renderer.

Abstract: Methods, apparatuses and streams are disclosed for transmitting tiled volumetric video and, at the receiver, for generating an atlas image compatible with a legacy decoder. At the server side, viewport information is obtained and a first list of central tiles and a second list of border tiles are selected. A central tile is a part of an image obtained by projecting the 3D scene onto an image plane according to a central point of view. A border tile is an image comprising dis-occluding patches. Sizes and shapes of border tiles are function of size and shape of central tiles. At the client side, tiles are arranged according to a layout selected in a set of layouts according to the number, sizes and shapes of border tiles. FIG. 8.

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.

Abstract: To represent a 3D scene, the MPI format uses a set of fronto-parallel planes. Different from MPI, the current MIV standard accepts a 3D scene represented as sequence input pairs of texture and depth pictures as input. To enable transmission of an MPI cube via the MIV-V3C standard, in one embodiment, an MPI cube is divided into empty regions and local MPI partitions that contain 3D objects. Each partition in the MPI cube can be projected to one or more patches. For a patch, the geometry is generated as well as the texture attribute and alpha attributes, and the alpha attributes may be represented as a peak and a width of an impulse. In another embodiment, an MPI RGBA layer of the MPI is cut into sub-images. Each sub-image may correspond to a patch, and the RGB and alpha information of the sub-image are assigned to the patch.

Abstract: Methods and device for encoding/decoding data representative of a 3D scene.

Abstract: Methods and devices for encoding and decoding data representative of a 3D scene are disclosed. A set of first patches is generated from a first MVD content acquired from a first region of the 3D scene. A patch is a part of one of the views of the MVD content. A set of second patches is generated from a second MVD content acquired from a second region of the 3D scene. An atlas packing first and second patches is generated and associated with metadata indicating, for a patch of the atlas, whether the patch is a first or a second patch At the decoding side, first patches are used for rendering the viewport image and second patches are used for pre-processing or post-processing the viewport image.

Abstract: A method for encoding a volumetric video content representative of a 3D scene is disclosed. The method comprises obtaining a reference viewing box and an intermediate viewing box defined within the 3D scene. For the reference viewing bounding box, the volumetric video reference subcontent is encoded as a central image and peripheral patches for parallax. For the intermediate viewing bounding box, the volumetric video intermediate sub-content is encoded as intermediate central patches which are differences between the intermediate central image and the reference central image.

Abstract: Methods, devices and stream for encoding, decoding and transmitting a multi-views frame are disclosed. In a multi-views frame some of the views are more trustable than others. The multi-views frame is encoded in a data stream in association with metadata that comprise, for at least one of the views, a parameter indicating a degree of confidence in the information carried by this view. This information is used at the decoding side to determine the contribution of the view when synthetizing pixels of a viewport frame for a given point of view in the 3D space.

Abstract: Methods, devices and streams are disclosed for encoding a depth atlas representative of the geometry of a volumetric video. Views to be encoded are analyzed to detect regions of the views with simple depth or color, that is regions for which the depth or color has a local variance lower than a given threshold. Resolution of such regions is reduced and the atlas comprises first regions in full resolution and downscaled second regions. Metadata indicating whether a patch is a downscaled region and, if so the downscaling factor, are associated with the atlas in the data stream. The decoder uses these metadata to compose the view from different patches.

Abstract: Methods, devices and data stream are provided for signaling and decoding information representative of restrictions of navigation in a volumetric video. The data stream comprises metadata associated to video data representative of the volumetric video. The metadata comprise data representative of a viewing bounding box, data representative of a curvilinear path in the 3D space of said volumetric video; and data representative of at least one viewing direction range associated with a point on the curvilinear path.

Abstract: Encoding/decoding data representative of a 3D representation of a scene according to a range of points of view can involve generating a depth map associated with a part of the 3D representation according to a parameter representative of a two-dimensional parameterization associated with the part and data associated with a point included in the part, wherein the two-dimensional parameterization can be responsive to geometric information associated with the point and to pose information associated with the range of points of view. A texture map associated with the part can be generated according to the parameter and data associated with the point. First information representative of point density of points in a part of the part can be obtained. The depth map, texture map, parameter, and first information can be included in respective syntax elements of a bitstream.

Abstract: A method and a device are disclosed to encode volumetric video in a patch-based atlas format in intra-periods of varying length. A first atlas layout is built for a first sequence of 3D scenes. The number of 3D scenes in the sequence is chosen to fit the size of a GoP of the codec. A second sequence is iteratively set up by appending the next 3D scene of the sequence to encode while the number of patches of the layout built for this iterative second sequence is lower than or equal to the number of patches of the first layout. When iterations end, one of the layouts is selected to generate every atlas of the group. In such a way, size of metadata is decreased and compression is enhanced.