Abstract: In one implementation, we propose to change the decoding process of blocks within V-PCC patches by directly decoding blocks at reduced resolutions, allowing a less computationally intensive rendering of the point cloud. In one example, based on the rendering information from the renderer, we evaluate for each patch, for each block component of the patches, or for each pixel of the patches, if the corresponding reconstructed point will be viewed by the user after the rendering process and which decimation level could be selected without impairing significantly the rendering quality. Based on the evaluation results, we decide whether to render or not the current area and at which resolution. In one approach, we compare the distance to the screen to a ranges of distance thresholds. In another approach, we compare the distance in the screen coordinate of the projection of two adjacent points of the block.

Abstract: An approach extends a Video-Point Cloud Compression codec approach to store mesh information and provide a good efficiency and a good objective and subjective quality. To reduce the quantity of data that needs to be transmitted, the approach removes occupancy maps that are used to know which parts of the patches are occupied. These occupancy maps create a lot of artifacts on the borders of the patches due to the occupancy map sub-resolution used to transmit the occupancy information. Instead, the approach transmits the 3-Dimensional borders of the patches (list of the 3D points constituting the borders of the patches) and uses this information to identify which parts of the 2D patches are occupied and connect the 3D reconstructed patches according to the real 3D borders of the patches.

Abstract: At least one embodiment relates to a method comprising encoding a projection mode associated with an image region of a first depth image, said projection mode indicating if said image region stores either the minimum or the maximum depth value of at least one orthogonally projected 3D point of the point cloud along a same projection direction; and encoding said depth minimum and maximum depth values as a function of said projection mode.

Abstract: At least one embodiment relates to a method for smoothing (filtering) the geometry of a point cloud frame by performing an analysis and filtering of said geometry point cloud in a 2D space, without reconstruction of 3D samples in a 3D space, and by using a flexible filtering operator that, in addition to moving existing points, can also remove points or add new ones.

Abstract: At least one embodiment relates to the transfer, between two processing units or memories, of a three-channels texture image and at least two image-structured data used for reconstructing the geometry of the point cloud. Such transfer comprises copying the three channels of the three-channels texture image into the three channels of a four-channels image, and storing, in the fourth channel of the four-channels image, a combined information obtained by combining altogether the at least two image-structured data. The four-channel image is then transferred.

Abstract: At least one embodiment relates to a method for transmitting PLRM metadata that removes the dependency between PLRM metadata and the occupancy map and the bloc to patch information BlockToPatch.

Abstract: At least a method and an apparatus are presented for efficiently encoding or decoding video. For example, a 2-D patch of the point cloud is obtained by projecting 3-D points of the point cloud onto a projection plane, the patch having a plurality of pixels. The patch is divided into a plurality of smaller blocks. The number of pixels is determined within each of the plurality of smaller blocks. An updated occupancy map is obtained based on the determined number of pixels within each of the plurality of smaller blocks. A reconstructed point cloud is obtained based on the updated occupancy map, wherein the reconstructed point cloud is a less dense representation of the point cloud.

Abstract: At least one embodiment relates to a method for signaling a syntax element representing a Point Local Reconstruction mode, said Point Local Reconstruction mode being representative of at least one parameter defining a mode for reconstructing at least one point of a point cloud frame.

Abstract: The present embodiments relate to a method and device. The method comprises obtaining at least one first point from at least one point of a point cloud by projecting said point of the point cloud onto a projection plane and obtaining at least one other point of the point cloud determined according to said at least one first point; determining and encoding at least one interpolation coding mode for said at least one first point based on at least one reconstructed point obtained from said at least one first point and at least one interpolation point defined by said at least one interpolation coding mode to approximate said at least one other point of the point cloud; and signaling said at least interpolation coding mode as values of image data.

Abstract: Described are methods and devices for adding at least one 3D sample to a point cloud frame and for assigning a color-coding mode to said at least one 3D sample, said color-coding mode indicating if color information associated with said at least one 3D sample is explicitly encoded in a bitstream or if said color information is implicit.

Abstract: At least one embodiment relates to a method for adding at least one 3D sample to a point cloud frame and for assigning a color-coding mode to said at least one 3D sample, said color-coding mode indicating if color information associated with said at least one 3D sample is explicitly encoded in a bitstream or if said color information is implicit.

Abstract: At least one embodiment relates to a method comprising encoding a projection mode associated with an image region of a first depth image, said projection mode indicating if said image region stores either the minimum or the maximum depth value of at least one orthogonally projected 3D point of the point cloud along a same projection direction; and encoding said depth minimum and maximum depth values as a function of said projection mode.

Abstract: This method comprises: —orthogonally projecting at least one point of a point cloud along projection lines; and —for at least two points of a same projection line, signaling in a bitstream whether a position of said projection line between a nearer and a farther points of said projection line is occupied or not.

Abstract: A method and device are provided for rendering an image. The method comprises receiving an image from at least two different camera positions and determining a camera orientation and at least one image attribute associated with each of the positions. A model is then generated of the image based on the attribute and camera orientation associated with the received camera positions of the image. The model is enabled to provide a virtual rendering of the image at a plurality viewing orientations and selectively providing appropriate attributes associated with the viewing orientation.

Abstract: A method and device for generating points of a 3D scene from a depth image. To reach that aim, depth information associated with a current pixel is compared with depth information associated with pixels spatially adjacent to the current pixel in the depth image. When the difference of depth between the current pixel and an adjacent pixel is greater than a first value and less than a second value, at least an additional point of said 3D scene is generated, in addition to a current point associated with the current pixel of the depth image, the number of additional points depending on the depth difference.

Abstract: At least one embodiment relates to a method and an apparatus for reconstructing an occupancy map comprising occupancy data of a volumetric content, wherein reconstructing the occupancy map comprises: —decoding the occupancy map at a first resolution, —determining a scale factor as a function of the first resolution, —upscaling the occupancy map by the scale factor, using a neural network.

Abstract: This method for inter-predictive encoding of a time-varying 3D point cloud including a series of successive frames divided in 3D blocks into at least one bitstream comprises encoding (20) 3D motion information including a geometric transformation comprising rotation information representative of a rotation transformation and translation information representative of a translation transformation, wherein the translation information comprises a vector ?T representing an estimation error of the translation transformation.

Abstract: The present principles a method and a device for encoding the colors of a point cloud (IPC) representing a 3D object. The method is characterized in that the method comprises: —obtaining (210) a set of points (SP) approximating the geometry of said point cloud (IPC); —encoding (220) a color information data indicating that the color of at least one of the point of said set of points is encoded in a bitstream and that the colors of the other points of said set of points are not encoded in the bitstream. The present principles also relates to a method and a device for decoding the colors of a point cloud.

Abstract: At least one embodiment relates to a method comprising encoding a projection mode associated with an image region of a first depth image, said projection mode indicating if said image region stores either the minimum or the maximum depth value of at least one orthogonally projected 3D point of the point cloud along a same projection direction; and encoding said depth minimum and maximum depth values as a function of said projection mode.

Abstract: The present embodiments relate to a method and device. The method comprises obtaining at least one first point from at least one point of a point cloud by projecting said point of the point cloud onto a projection plane and obtaining at least one other point of the point cloud determined according to said at least one first point; determining and encoding at least one interpolation coding mode for said at least one first point based on at least one reconstructed point obtained from said at least one first point and at least one interpolation point defined by said at least one interpolation coding mode to approximate said at least one other point of the point cloud; and signaling said at least interpolation coding mode as values of image data.