中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
LC-NeRF: Local Controllable Face Generation in Neural Radiance Field

文献类型：期刊论文

作者Zhou, Wen-Yang1; Yuan, Lu2; Chen, Shu-Yu3; Gao, Lin3; Hu, Shi-Min1
刊名IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
出版日期2024-08-01
卷号30期号:8页码:5437-5448
关键词Geometry Faces Three-dimensional displays Generators Semantics Codes Controllability 3D face generation neural radiance fields semantic manipulation
ISSN号1077-2626
DOI10.1109/TVCG.2023.3293653
英文摘要3D face generation has achieved high visual quality and 3D consistency thanks to the development of neural radiance fields (NeRF). However, these methods model the whole face as a neural radiance field, which limits the controllability of the local regions. In other words, previous methods struggle to independently control local regions, such as the mouth, nose, and hair. To improve local controllability in NeRF-based face generation, we propose LC-NeRF, which is composed of a Local Region Generators Module (LRGM) and a Spatial-Aware Fusion Module (SAFM), allowing for geometry and texture control of local facial regions. The LRGM models different facial regions as independent neural radiance fields and the SAFM is responsible for merging multiple independent neural radiance fields into a complete representation. Finally, LC-NeRF enables the modification of the latent code associated with each individual generator, thereby allowing precise control over the corresponding local region. Qualitative and quantitative evaluations show that our method provides better local controllability than state-of-the-art 3D-aware face generation methods. A perception study reveals that our method outperforms existing state-of-the-art methods in terms of image quality, face consistency, and editing effects. Furthermore, our method exhibits favorable performance in downstream tasks, including real image editing and text-driven facial image editing.
资助项目National Key R&D Program of China[2021ZD0112902] ; Natural Science Foundation of China[62220106003] ; Research Grant of Beijing Higher Institution Engineering Research Center ; Tsinghua-Tencent Joint Laboratory for Internet Innovation Technology
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001262914400031
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/39840]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Hu, Shi-Min
作者单位1.Tsinghua Univ, BNRist, Beijing 100084, Peoples R China
2.Stanford Univ, Dept Comp Sci, Stanford, CA 94305 USA
3.Chinese Acad Sci, Inst Comp Technol, Beijing 100045, Peoples R China
推荐引用方式
GB/T 7714		 Zhou, Wen-Yang,Yuan, Lu,Chen, Shu-Yu,et al. LC-NeRF: Local Controllable Face Generation in Neural Radiance Field[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2024,30(8):5437-5448.
APA Zhou, Wen-Yang,Yuan, Lu,Chen, Shu-Yu,Gao, Lin,&Hu, Shi-Min.(2024).LC-NeRF: Local Controllable Face Generation in Neural Radiance Field.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,30(8),5437-5448.
MLA Zhou, Wen-Yang,et al."LC-NeRF: Local Controllable Face Generation in Neural Radiance Field".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 30.8(2024):5437-5448.

入库方式： OAI收割

来源：计算技术研究所

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。