arrow
返回

Structure-aware neural radiance fields without posed camera

delete2024-07-01
delete2
PRE
AI
S
Shu Chen *
Y
Yang Zhang
Y
Yaxin Xu
B
Beiji Zou
DOI:10.1016/j.patcog.2024.110419delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
The neural radiance fields (NeRF) for realistic novel view synthesis require camera poses to be pre -acquired by a structure -from -motion (SfM) approach. This two -stage strategy is not convenient to use and degrades the performance because the error in the pose extraction can propagate to the view synthesis. We integrate pose extraction and view synthesis into a jointly optimized process so that they can benefit from each other. For network training, only images are given without pre -known camera poses. The camera poses are obtained by the depth -consistent constraint in which the identical feature in different views has the same world coordinates transformed from the local camera coordinates according to the extracted poses. The depth -consistent constraint is jointly optimized with the pixel color constraint. The poses are represented by a CNN -based deep network, whose input is the related frames. This joint optimization enables NeRF to be aware of the scene's structure, resulting in improved generalization performance. Experiments on three datasets demonstrate the effectiveness of camera pose estimation and novel view synthesis. Code is available at https://github.com/XTU-PR-LAB/SaNerf.
Keyword:
Neural radiance fields
Depth consistent constraint
Novel view synthesis

期刊

Pattern Recognition 封面图
Pattern Recognition
IF:
7.6
论文数:
1.3W
被引数:
4.5W

机构

C
Central South University
学者数:
10.0W
论文数: 7.2W
被引数: 10.9W
X
xiangtan university
学者数:
1.5W
论文数: 9.2K
被引数: 8
引用论文

引用论文

Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines局部光场融合: 具有规定采样指南的实用视图合成
err2019-07-12
err612
errOAAI
errMildenhall, Ben; Srinivasan, Pratul P.; Ortiz-Cayon, Rodrigo; Kalantari, Nima Khademi; Ramamoorthi, Ravi; Ng, Ren; Kar, Abhishek
err分享
err收藏
Effect of poly(lactic acid) crystallization on its mechanical and heat resistance performances
err2021-01-01
err0
PREAI
errBomou Ma; Xueli Wang; Yong He; Zhen Dong; Xu Zhang; Xiao Chen; Tianxi Liu
err分享
err收藏
CD133-targeted delivery of self-assembled PEGylated carboxymethylcellulose-SN38 nanoparticles to colorectal cancer
err2018-03-08
err0
errOAAI
errMona Alibolandi; Khalil Abnous; Sajjad Anvari; Marzieh Mohammadi; Mohammad Ramezani; Seyed Mohammad Taghdisi
err分享
err收藏
学者 查看更多内容