Invention Application
- Patent Title: LEARNING 2D TEXTURE MAPPING IN VOLUMETRIC NEURAL RENDERING
-
Application No.: US17559867Application Date: 2021-12-22
-
Publication No.: US20220198738A1Publication Date: 2022-06-23
- Inventor: Zexiang XU , Yannick HOLD-GEOFFROY , Milos HASAN , Kalyan SUNKAVALLI , Fanbo XIANG
- Applicant: Adobe Inc.
- Applicant Address: US CA San Jose
- Assignee: Adobe Inc.
- Current Assignee: Adobe Inc.
- Current Assignee Address: US CA San Jose
- Main IPC: G06T15/04
- IPC: G06T15/04 ; G06T15/20 ; G06T19/20 ; G06N3/04 ; G06N3/08

Abstract:
Embodiments are disclosed for neural texture mapping. In some embodiments, a method of neural texture mapping includes obtaining a plurality of images of an object, determining volumetric representation of a scene of the object using a first neural network, mapping 3D points of the scene to a 2D texture space using a second neural network, and determining radiance values for each 2D point in the 2D texture space from a plurality of viewpoints using a second neural network to generate a 3D appearance representation of the object.
Public/Granted literature
- US11887241B2 Learning 2D texture mapping in volumetric neural rendering Public/Granted day:2024-01-30
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 |
G06T15/00 | 3D〔三维〕图像的加工 |
G06T15/04 | .纹理映射 |