消息
×
loading..
Neural Reconstruction through Scattering Media with Forward and Backward Losses
2023-07-28
会议录名称2023 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL PHOTOGRAPHY (ICCP)
ISSN2164-9774
发表状态已发表
DOI10.1109/ICCP56744.2023.10233796
摘要Reconstructing an object behind a scattering medium needs to tackle different light scatterings inside the medium and in the free space. Major approaches, e.g., diffuse optical tomography and non-line-of-sight imaging, address either of the light scatterings. Confocal diffuse tomography (CDT) considers the media acting as a diffuse kernel on the free-space scattering and recovers the object by deconvolving the inside-medium scattering. Inspired by CDT, we present a Neural De-Scatterer to solve this challenging problem. We exploit neural implicit fields to represent the the free-space scattering and use a multilayer perceptron (MLP) to learn the density and albedo of the hidden object. Furthermore, we tailor a bi-directional training strategy to optimize the MLP with forward and backward losses and employ hash encoding for memory and computation efficiency. The Neural De-Scatterer enables us to reconstruct objects at arbitrary resolution. Comprehensive experiments with synthetic and real measurements demonstrate that our Neural De-Scatterer outperforms state-of-The-Art methods. Our data and code are publicly available. © 2023 IEEE.
会议录编者/会议主办者et al. ; KLA+ ; PI Imaging ; Snap Inc. ; Sony ; Ubicept
关键词Computational photography Diffuse optical tomography Non-line-of-sight imaging Neural implicit representation
会议名称15th IEEE International Conference on Computational Photography, ICCP 2023
会议地点Madison, WI, USA
会议日期28-30 July 2023
URL查看原文
收录类别EI
语种英语
出版者Institute of Electrical and Electronics Engineers Inc.
EI入藏号20234014830080
EI主题词Light scattering
EI分类号711 Electromagnetic Waves ; 741.1 Light/Optics ; 741.3 Optical Devices and Systems ; 742.1 Photography
原始文献类型Conference article (CA)
来源库IEEE
引用统计
正在获取...
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/333447
专题信息科学与技术学院
信息科学与技术学院_PI研究组_虞晶怡组
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 201210, China
2.Shanghai Engineering Research Center of Intelligent Vision and Imaging and also with the School of Information Science and Technology, ShanghaiTech University, Shanghai 201210, 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
Yuehan Wang,Siyuan Shen,Suan Xia,et al. Neural Reconstruction through Scattering Media with Forward and Backward Losses[C]//et al., KLA+, PI Imaging, Snap Inc., Sony, Ubicept:Institute of Electrical and Electronics Engineers Inc.,2023.
条目包含的文件
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
[Yuehan Wang]的文章
[Siyuan Shen]的文章
[Suan Xia]的文章
百度学术
百度学术中相似的文章
[Yuehan Wang]的文章
[Siyuan Shen]的文章
[Suan Xia]的文章
必应学术
必应学术中相似的文章
[Yuehan Wang]的文章
[Siyuan Shen]的文章
[Suan Xia]的文章
相关权益政策
暂无数据
收藏/分享
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。