Non-line-of-Sight Imaging via Neural Transient Fields
Siyuan Shen1; Zi Wang2; Ping Liu1; Zhengqing Pan1; Ruiqian Li1; Tian Gao3; Shiying Li4; Jingyi Yu4
2021-07-01
发表期刊IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN0162-8828
EISSN1939-3539
卷号43期号:7页码:2257-2268
发表状态已发表
DOI10.1109/TPAMI.2021.3076062
摘要

We present a neural modeling framework for non-line-of-sight (NLOS) imaging. Previous solutions have sought to explicitly recover the 3D geometry (e.g., as point clouds) or voxel density (e.g., within a pre-defined volume) of the hidden scene. In contrast, inspired by the recent Neural Radiance Field (NeRF) approach, we use a multi-layer perceptron (MLP) to represent the neural transient field or NeTF. However, NeTF measures the transient over spherical wavefronts rather than the radiance along lines. We therefore formulate a spherical volume NeTF reconstruction pipeline, applicable to both confocal and non-confocal setups. Compared with NeRF, NeTF samples a much sparser set of viewpoints (scanning spots) and the sampling is highly uneven. We thus introduce a Monte Carlo technique to improve the robustness in the reconstruction. Experiments on synthetic and real datasets demonstrate NeTF achieves state-of-the-art performance and can provide reliable reconstructions even under semi-occlusions and on non-Lambertian materials.

关键词Computational photography non-line-of-sight imaging neural radiance field neural rendering
URL查看原文
收录类别SCIE ; EI
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000659549700007
出版者IEEE COMPUTER SOC
原始文献类型Article
来源库IEEE
引用统计
文献类型期刊论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/127562
专题信息科学与技术学院
物质科学与技术学院
信息科学与技术学院_PI研究组_虞晶怡组
物质科学与技术学院_本科生
信息科学与技术学院_硕士生
信息科学与技术学院_博士生
作者单位1.School of Information Science and Technology, ShanghaiTech University, Shanghai, China
2.Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, China
3.School of Physical Science and Technology, ShanghaiTech University, Shanghai, China
4.Shanghai Engineering Research Center of Intelligent Vision and Imaging, ShanghaiTech University, Shanghai, China
第一作者单位信息科学与技术学院
第一作者的第一单位信息科学与技术学院
推荐引用方式
GB/T 7714
Siyuan Shen,Zi Wang,Ping Liu,et al. Non-line-of-Sight Imaging via Neural Transient Fields[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2021,43(7):2257-2268.
APA Siyuan Shen.,Zi Wang.,Ping Liu.,Zhengqing Pan.,Ruiqian Li.,...&Jingyi Yu.(2021).Non-line-of-Sight Imaging via Neural Transient Fields.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,43(7),2257-2268.
MLA Siyuan Shen,et al."Non-line-of-Sight Imaging via Neural Transient Fields".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 43.7(2021):2257-2268.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Siyuan Shen]的文章
[Zi Wang]的文章
[Ping Liu]的文章
百度学术
百度学术中相似的文章
[Siyuan Shen]的文章
[Zi Wang]的文章
[Ping Liu]的文章
必应学术
必应学术中相似的文章
[Siyuan Shen]的文章
[Zi Wang]的文章
[Ping Liu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 10.1109@TPAMI.2021.3076062.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。