Invention Grant
- Patent Title: Convex representation of objects using neural network
-
Application No.: US16847009Application Date: 2020-04-13
-
Publication No.: US11508167B2Publication Date: 2022-11-22
- Inventor: Boyang Deng , Kyle Genova , Soroosh Yazdani , Sofien Bouaziz , Geoffrey E. Hinton , Andrea Tagliasacchi
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06T17/00
- IPC: G06T17/00 ; G06V20/64 ; G06N3/08 ; G06N3/04

Abstract:
Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating convex decomposition of objects using neural network models. One of the methods includes receiving an input that depicts an object. The input is processed using a neural network to generate an output that defines a convex representation of the object. The output includes, for each of a plurality of convex elements, respective parameters that define a position of the convex element in the convex representation of the object.
Public/Granted literature
- US20210319209A1 Convex Representation of Objects Using Neural Network Public/Granted day:2021-10-14
Information query
IPC分类:
G | 物理 |
G06 | 计算;推算或计数 |
G06T | 一般的图像数据处理或产生 |
G06T17/00 | 用于计算机制图的3D建模 |