| |||||||
ShanghaiTech University Knowledge Management System
3D face reconstruction using color photometric stereo with uncalibrated near point lights | |
2020 | |
会议录名称 | 2020 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL PHOTOGRAPHY, ICCP 2020 |
ISSN | 2164-9774 |
页码 | 1-12 |
发表状态 | 已发表 |
DOI | 10.1109/ICCP48838.2020.9105199 |
摘要 | We present a new color photometric stereo (CPS) method that recovers high quality, detailed 3D face geometry in a single shot. Our system uses three uncalibrated near point lights of different colors and a single camera. For robust self-calibration of the light sources, we use 3D morphable model (3DMM) [1] and semantic segmentation of facial parts. For reconstruction, we address the inherent spectral ambiguity in color photometric stereo by incorporating albedo consensus, albedo similarity, and proxy prior into a unified framework. In this way, we jointly exploit multiple cues to resolve under-determinedness, without the need for spatial constancy of albedo. Experiments show that our new approach produces state-of-the-art results from single image with high-fidelity geometry that includes details such as wrinkles. © 2020 IEEE. |
关键词 | Color photometric stereo 3D face reconstruction uncalibrated near point lights single shot capture normal estimation |
会议地点 | Saint Louis, MO, United states |
会议日期 | 24-26 April 2020 |
URL | 查看原文 |
收录类别 | EI ; CPCI ; CPCI-S |
资助项目 | [2019-01-07-00-01-E00003] ; Science and Technology Commission of Shanghai Municipality[2015F0203-000-06] ; National Basic Research Program of China (973 Program)[2018YFB2100500] ; National Natural Science Foundation of China[61976138] |
出版者 | Institute of Electrical and Electronics Engineers Inc. |
EI入藏号 | 20202508856289 |
EI主题词 | 3D modeling ; Color ; Image reconstruction ; Light sources ; Photometry ; Semantics ; Solar radiation ; Stereo image processing |
EI分类号 | Solar Energy and Phenomena:657.1 ; Data Processing and Image Processing:723.2 ; Light/Optics:741.1 ; Photography:742.1 ; Optical Variables Measurements:941.4 |
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/122304 |
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 |
作者单位 | 1.University of Chinese Academy of Sciences, China 2.DGene Inc., Baton Rouge, LA, USA 3.Zillow Group, Seattle, WA, USA 4.School of Information Science and Technology, ShanghaiTech University, Shanghai, China |
推荐引用方式 GB/T 7714 | Zhang Chen,Yu Ji,Mingyuan Zhou,et al. 3D face reconstruction using color photometric stereo with uncalibrated near point lights[C]:Institute of Electrical and Electronics Engineers Inc.,2020:1-12. |
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 |
[Zhang Chen]的文章 |
[Yu Ji]的文章 |
[Mingyuan Zhou]的文章 |
百度学术 |
百度学术中相似的文章 |
[Zhang Chen]的文章 |
[Yu Ji]的文章 |
[Mingyuan Zhou]的文章 |
必应学术 |
必应学术中相似的文章 |
[Zhang Chen]的文章 |
[Yu Ji]的文章 |
[Mingyuan Zhou]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
修改评论
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。