-
公开(公告)号:US20240127489A1
公开(公告)日:2024-04-18
申请号:US18114910
申请日:2023-02-27
Applicant: SONY GROUP CORPORATION , Sony Corporation of America
Inventor: Danillo Graziosi
Abstract: A method is disclosed to generate (u,v) coordinates at the decoder side by using parameters of orthographic projection functions, transmitted via an atlas bitstream. With the parameters for orthographic projection, the decoder is able to efficiently generate (u,v) coordinates and avoid their expensive coding.
-
公开(公告)号:US20230016302A1
公开(公告)日:2023-01-19
申请号:US17861033
申请日:2022-07-08
Applicant: SONY GROUP CORPORATION , Sony Corporation of America
Inventor: Alexandre Zaghetto , Danillo Graziosi , Ali Tabatabai
IPC: G06T9/00
Abstract: Methods, systems and device for efficiently compressing task-oriented dynamic meshes using occupancy networks are described herein. A single trained occupancy network model is able to reconstruct a mesh video using a few additional points per input mesh frame. To optimize the compression of the model and points, the estimated rate to compress the occupancy network is able to be included in the loss function. This minimizes the number of bits to encode the model, while it tries to reproduce the meshes as well as possible. An adaptive subsampling per input mesh is added to optimize the mesh reconstruction and the N-point point clouds compression. To optimize the model to perform a particular task, a metric is added to the cost function that takes this task into account.
-
公开(公告)号:US20230013421A1
公开(公告)日:2023-01-19
申请号:US17828326
申请日:2022-05-31
Applicant: SONY GROUP CORPORATION , Sony Corporation of America
Inventor: Danillo Graziosi , Alexandre Zaghetto , Ali Tabatabai
IPC: H04N19/597 , G06V10/764 , G06V10/82 , G06V20/64 , H04N19/13 , H04N19/167 , H04N19/29 , H04N19/436 , H04N19/132
Abstract: Occupancy networks enable efficient and flexible point cloud compression. In addition to the voxel-based representation, occupancy networks are able to handle points, meshes, or projected images of 3D objects, making them very flexible in terms of input signal representation. The probability of occupancy of positions is estimated using occupancy networks instead of sparse convolutional neural networks. A compression implementation using occupancy network enables scalability with infinite reconstruction resolution.
-
公开(公告)号:US10964102B2
公开(公告)日:2021-03-30
申请号:US16423940
申请日:2019-05-28
Applicant: SONY CORPORATION
Inventor: Arash Vosoughi , Danillo Graziosi
Abstract: An electronic apparatus and method for adaptive sub-band based coding of hierarchical transform coefficients of a 3D point cloud, is provided. The electronic apparatus stores the 3D point cloud and generates a plurality of voxels from the 3D point cloud. The electronic apparatus generates a plurality of hierarchical transform coefficients by application of a hierarchical transform scheme on the generated plurality of voxels and classifies the plurality of hierarchical transform coefficients into a plurality of sub-bands of hierarchical transform coefficients. The plurality of hierarchical transform coefficients are classified based on a weight of each of the plurality of hierarchical transform coefficients. The electronic apparatus further generates a plurality of quantized levels by application of a different quantization scheme of a set of different quantization schemes on each sub-band of hierarchical transform coefficients of the plurality of sub-bands of hierarchical transform coefficients and encodes the generated plurality of quantized levels.
-
5.
公开(公告)号:US20200090374A1
公开(公告)日:2020-03-19
申请号:US16266340
申请日:2019-02-04
Applicant: SONY CORPORATION
Inventor: Danillo Graziosi , Arash Vosoughi
Abstract: A method for rate distortion optimization for adaptive sub-band coding of Region-Adaptive Hierarchical Transform (RAHT) coefficients, which is a point cloud color compression method adopted in PCC test model TMC13 for compression of CAT1 sequences is described herein. Based on Lagrangian optimization, the method estimates the coefficient distortion by using the compressed mesh geometry as reference. The Lagrange factor is calculated based on the quantization parameters, and the results show that the parameters obtained automatically have similar or better performance than parameters chosen after an extensive search.
-
6.
公开(公告)号:US12273545B2
公开(公告)日:2025-04-08
申请号:US17828392
申请日:2022-05-31
Applicant: SONY GROUP CORPORATION , Sony Corporation of America
Inventor: Danillo Graziosi , Alexandre Zaghetto , Ali Tabatabai
IPC: H04N19/42 , G06N3/082 , G06V10/764 , G06V10/82 , H04N19/597
Abstract: Methods, systems and devices described herein implement a task-driven machine learning-based compression scheme for point cloud geometry implicit representation. The machine learning-based codec is able to be optimized for a task to achieve better compression rates by being conditioned to what the reconstructed signal will be used for. The latent representation of the point cloud or the neural network that implicitly represents the point cloud itself are able to be compressed. The methods described herein perform efficient compression of the implicit representation of a point cloud given a target task.
-
公开(公告)号:US20250022179A1
公开(公告)日:2025-01-16
申请号:US18394062
申请日:2023-12-22
Applicant: Sony Group Corporation , Sony Corporation of America
Inventor: Danillo Graziosi , Alexandre Zaghetto , Ali Tabatabai
IPC: G06T9/00 , G06F18/2431 , G06T7/11 , G06T7/187 , G06T17/20
Abstract: Described herein is a method to segment meshes into sub-meshes based on triangle properties. The triangles are first classified according to some characteristic using their respective areas. A filtering process may change the classification according to the neighboring triangles. Then connected components are generated, and neighboring connected components are merged following a certain criteria. In some embodiments, connected components that share the most amount of edges are merged. With this technique, sub-meshes can be automatically generated without any previous knowledge of the mesh generation stage.
-
公开(公告)号:US20230306644A1
公开(公告)日:2023-09-28
申请号:US17987848
申请日:2022-11-15
Applicant: SONY GROUP CORPORATION , Sony Corporation of America
Inventor: Danillo Graziosi , Alexandre Zaghetto , Ali Tabatabai
Abstract: New syntax elements are used to extend patch types, and the syntax is added to the V3C standard. The new syntax defines patches that encode meshes by projecting connected triangles to a 2D surface, patches that encode triangles or triangle strips without any projection, or patches that are tracked over time and are encoded by projecting connected triangles to a 2D surface. Furthermore, the syntax allows for different ways of coding the mesh-specific information. For instance, the syntax enables three different encoding methods for the vertex position: explicit (directly added to the atlas stream), embedded on video data (occupancy map data), or encoded using an external mesh encoder.
-
9.
公开(公告)号:US20230025378A1
公开(公告)日:2023-01-26
申请号:US17828392
申请日:2022-05-31
Applicant: SONY GROUP CORPORATION , Sony Corporation of America
Inventor: Danillo Graziosi , Alexandre Zaghetto , Ali Tabatabai
IPC: H04N19/42 , H04N19/597 , G06V10/764 , G06V10/82 , G06N3/08
Abstract: Methods, systems and devices described herein implement a task-driven machine learning-based compression scheme for point cloud geometry implicit representation. The machine learning-based codec is able to be optimized for a task to achieve better compression rates by being conditioned to what the reconstructed signal will be used for. The latent representation of the point cloud or the neural network that implicitly represents the point cloud itself are able to be compressed. The methods described herein perform efficient compression of the implicit representation of a point cloud given a target task.
-
公开(公告)号:US11368693B2
公开(公告)日:2022-06-21
申请号:US16812117
申请日:2020-03-06
Applicant: SONY CORPORATION
Inventor: Alexandre Zaghetto , Danillo Graziosi , Ali Tabatabai
IPC: H04N11/02 , H04N19/124 , G06T9/40 , H04N19/44
Abstract: A quantization scheme substitutes the division operation by forward and inverse quantization look-up tables to improve efficiency.
-
-
-
-
-
-
-
-
-