Neural Reflectance Decomposition Under Dynamic Point Light
文献类型：期刊论文
| 作者 | Li, Yuandong3; Hu, Qinglei2,3,4; Ouyang, Zhenchao2; Shen, Shuhan1,5
|
| 刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
 |
| 出版日期 | 2024-04-01 |
| 卷号 | 34期号:4页码:2195-2208 |
| 关键词 | 3D reconstruction differentiable rendering self-supervised |
| ISSN号 | 1051-8215 |
| DOI | 10.1109/TCSVT.2023.3302389 |
| 通讯作者 | Hu, Qinglei(huql_buaa@buaa.edu.cn) |
| 英文摘要 | Decomposing a scene into its 3D geometry, surface material textures, and illumination is a challenging but important problem in computer vision and graphics. While recent neural implicit representation based works have shown tremendous advantages, existing methods are not applicable to images illuminated by a single dynamic point light. We propose an entirely self-supervised end-to-end neural implicit representation based reflectance decomposition algorithm for objects under a dynamic point light. Our method adopts a staged training framework to estimate the geometry, light source position, and surface material textures through volume rendering, self-shadow inverse rendering, and physical model based surface rendering respectively. This scheme allows accurate recovery of the surface material textures which are coupled to the dynamic light, improving the reflectance decomposition capability. For evaluation, we collect a new dataset of several synthetic and real world objects illuminated by a moving point light. Experiments show that our method achieves superior reflectance decomposition performance compared to state-of-the-art methods, and the recovered elements can be deployed in existing graphics pipelines to perform relighting, material editing, and scene composition. |
| WOS关键词 | SOURCE POSITION ; RECONSTRUCTION ; IMAGES ; SHAPE |
| 资助项目 | National Natural Science Foundation of China |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001197960500068 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/57023]  |
| 专题 | 精密感知与控制研究中心_精密感知与控制 |
| 通讯作者 | Hu, Qinglei |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Beihang Univ, Zhongfa Aviat Inst, Hangzhou 311115, Peoples R China 3.Beihang Univ, Sch Automat Sci & Elect Engn, Beijing 100191, Peoples R China 4.Tianmushan Lab, Hangzhou 310023, Peoples R China 5.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Yuandong,Hu, Qinglei,Ouyang, Zhenchao,et al. Neural Reflectance Decomposition Under Dynamic Point Light[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2024,34(4):2195-2208. |
| APA | Li, Yuandong,Hu, Qinglei,Ouyang, Zhenchao,&Shen, Shuhan.(2024).Neural Reflectance Decomposition Under Dynamic Point Light.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,34(4),2195-2208. |
| MLA | Li, Yuandong,et al."Neural Reflectance Decomposition Under Dynamic Point Light".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 34.4(2024):2195-2208. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。