公开(公告)号：US11107249B2

公开(公告)日：2021-08-31

申请号：US16655673

申请日：2019-10-17

Applicant: SONY CORPORATION

Inventor： Danillo Graziosi

IPC: G06K9/00 ,  G06T9/00 ,  G06K9/62

Abstract: A method of mapping 3D point cloud data into 2D surfaces for further efficient temporal coding is described herein. Point cloud global tetris packing utilizes 3D surface patches to represent point clouds and performs temporally consistent global mapping of 3D patch surface data into 2D canvas images. Point cloud global tetris packing includes calculating an accumulated occupancy map and a weight of each patch according to the matched patches.

公开(公告)号：US11076152B2

公开(公告)日：2021-07-27

申请号：US16525118

申请日：2019-07-29

Applicant: SONY CORPORATION

Inventor： Alexandre Zaghetto ,  Danillo Graziosi ,  Ali Tabatabai

IPC: H04N7/12 ,  H04N19/124 ,  H04N19/597 ,  H04N19/136 ,  H04N19/186

Abstract: A technique to parameterize the quantization scheme of the attribute coding of point cloud compression algorithms is described herein. Based on fixed-point arithmetic, the algorithm calculates the quantization step size (QS) in fixed-point notation, given a user-input quantization parameter (QP).

公开(公告)号：US11030777B2

公开(公告)日：2021-06-08

申请号：US16266332

申请日：2019-02-04

Applicant: SONY CORPORATION

Inventor： Danillo Graziosi ,  Arash Vosoughi

IPC: G06K9/00 ,  G06T9/00 ,  G06T15/00

Abstract: Lifting is a transform designed for color compression of point clouds which is adopted in one of the MPEG test models. The performance of lifting is improved herein. All the lifting coefficients are first divided into several subbands based on their assigned weights, which indicate the level of importance of each coefficient. Then, for each subband, a set of three dead-zones are derived for the three color components. The dead-zones of Cb and Cr channels are typically larger than that of Luma channel. In the original lifting scheme, Chroma is not suppressed at all. In contrast, as described herein, the size of the dead-zone is increased for different color components, which means that more quality (and bandwidth) is able to be adaptively provided for luminance coefficients than chrominance coefficients.

公开(公告)号：US10853975B2

公开(公告)日：2020-12-01

申请号：US16246975

申请日：2019-01-14

Applicant: SONY CORPORATION

Inventor： Arash Vosoughi ,  Danillo Graziosi

IPC: G06T15/00 ,  G06T9/40 ,  G06T15/40 ,  G06T15/04 ,  H04L29/08

Abstract: An apparatus receives a video which includes at least one three-dimensional (3D) object in a 3D physical space. A 3D geometrical representation of a point cloud is generated based on the video. The 3D geometrical representation of the point cloud includes a first set of points associated with geometrical information and texture information corresponding to the at least one 3D object. A plurality of two-dimensional (2D) projections are generated from the 3D geometrical representation of the point cloud. A second set of points that are occluded in the first set of points is detected, corresponding to the plurality of 2D projections. The plurality of 2D projections and the second set of points are distinctly encoded, and the remaining points, other than the detected second set of points, in the first set of points are discarded for efficient compression of the 3D geometrical representation of the point cloud.

公开(公告)号：US20200302648A1

公开(公告)日：2020-09-24

申请号：US16655673

申请日：2019-10-17

Applicant: SONY CORPORATION

Inventor： Danillo Graziosi

IPC: G06T9/00 ,  G06K9/62

Abstract: A method of mapping 3D point cloud data into 2D surfaces for further efficient temporal coding is described herein. Point cloud global tetris packing utilizes 3D surface patches to represent point clouds and performs temporally consistent global mapping of 3D patch surface data into 2D canvas images.

公开(公告)号：US10735766B2

公开(公告)日：2020-08-04

申请号：US16408099

申请日：2019-05-09

Applicant: SONY CORPORATION

Inventor： Danillo Graziosi

IPC: G06T9/00 ,  H04N19/597 ,  H04N19/182 ,  H04N19/176 ,  H04N19/91 ,  H04N19/80

Abstract: A method for coding auxiliary information of 3D point cloud data is described herein. The coding method utilizes 3D surface patches to represent point clouds, and performs flexible mapping of 3D patch surface data into 2D canvas images. Auxiliary data is transmitted in order to correctly identify and reconstruct the 3D patches from 2D information. The auxiliary data is encoded using a video encoder.

公开(公告)号：US10650554B2

公开(公告)日：2020-05-12

申请号：US16234179

申请日：2018-12-27

Applicant: SONY CORPORATION

Inventor： Danillo Graziosi

IPC: G06T9/00 ,  G06T15/04

Abstract: A novel method for signaling the packing method of 2D patches in canvas images, used in coding of 3D point clouds is described herein. The method utilizes a signal representation to indicate the orientation method to be used by the patches. Furthermore, an optimal method of coding the orientation information of each patch is described.

公开(公告)号：US20190392651A1

公开(公告)日：2019-12-26

申请号：US16234133

申请日：2018-12-27

Applicant: SONY CORPORATION

Inventor： Danillo Graziosi

IPC: G06T19/20 ,  G06T13/20

Abstract: A method of motion compensation for geometry representation of 3D data is described herein. The method performs motion compensation by first identifying correspondent 3D surfaces in time domain, then followed by a 3D to 2D projection of motion compensated 3D surface patches, and then finally performing 2D motion compensation on the projected 3D surface patches.

公开(公告)号：US20250111546A1

公开(公告)日：2025-04-03

申请号：US18758246

申请日：2024-06-28

Applicant: SONY GROUP CORPORATION ,  Sony Corporation of America

Inventor： Alexandre Zaghetto ,  Danillo Graziosi ,  Ali Tabatabai

IPC: G06T9/00 ,  G06T7/40 ,  G06T7/90

Abstract: A novel method of classifying point cloud data by extending the Gray-level Co-occurrence Matrix (GLCM) technique from the 2D to the sparse 3D domain is described herein. The method is able to be applied to point clouds derived from a mesh collection/meshes (such as, the Real-World Textured Things (RWTT) mesh collection). Implementations designed for multiple purposes are described herein: sampling and quantization of RWTT meshes, generation of GLCMs and corresponding texture descriptors, and the selection of potential candidate point clouds based on these extracted descriptors.

公开(公告)号：US12183045B2

公开(公告)日：2024-12-31

申请号：US17987841

申请日：2022-11-15

Applicant: SONY GROUP CORPORATION ,  Sony Corporation of America

Inventor： Danillo Graziosi ,  Alexandre Zaghetto ,  Ali Tabatabai

IPC: G06T9/00

Abstract: Ways to simplify connectivity data for patches are described herein. The patches are generated considering the high-resolution mesh information. The connectivity data is simplified at the patch level, while the geometry image is still preserved. For the connectivity simplification, only triangles inside the patch are simplified. If the border is still preserved, the reconstruction in 3D will not suffer from artifacts. The high-resolution geometry image can be used to reverse the simplification and improve the connectivity at the decoder side. Three embodiments of patch mesh simplification are described: quadric error edge collapse, border distance edge collapse, and border triangles only.