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
Text2Face: Text-Based Face Generation With Geometry and Appearance Control

文献类型：期刊论文

作者Zhang, Zhaoyang1; Chen, Junliang4; Fu, Hongbo5; Zhao, Jianjun4; Chen, Shu-Yu2,3; Gao, Lin2,3
刊名IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
出版日期2024-09-01
卷号30期号:9页码:6481-6492
关键词Faces Geometry Feature extraction Semantics Pipelines Nose Image synthesis Image generation face editing sketching interface text-based user interaction
ISSN号1077-2626
DOI10.1109/TVCG.2023.3349050
英文摘要Recent years have witnessed the emergence of various techniques proposed for text-based human face generation and manipulation. Such methods, targeting bridging the semantic gap between text and visual contents, provide users with a deft hand to turn ideas into visuals via text interface and enable more diversified multimedia applications. However, due to the flexibility of linguistic expressiveness, the mapping from sentences to desired facial images is clearly many-to-many, causing ambiguities during text-to-face generation. To alleviate these ambiguities, we introduce a local-to-global framework with two graph neural networks (one for geometry and the other for appearance) embedded to model the inter-dependency among facial parts. This is based upon our key observation that the geometry and appearance attributes among different facial components are not mutually independent, i.e., the combinations of part-level facial features are not arbitrary and thus do not conform to a uniform distribution. By learning from the dataset distribution and enabling recommendations given partial descriptions of human faces, these networks are highly suitable for our text-to-face task. Our method is capable of generating high-quality attribute-conditioned facial images from text. Extensive experiments have confirmed the superiority and usability of our method over the prior art.
资助项目National Natural Science Foundation of China[62061136007] ; National Natural Science Foundation of China[62102403] ; Beijing Municipal Natural Science Foundation for Distinguished Young Scholars[JQ21013] ; Beijing Municipal Science and Technology Commission[Z231100005923031]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001283711000023
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/39657]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Gao, Lin
作者单位1.Yale Univ, Dept Comp Sci, New Haven, CT 06520 USA
2.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
4.Beijing Film Acad, Dept Film & TV Technol, Beijing 100088, Peoples R China
5.City Univ Hong Kong, Sch Creat Media, Kowloon, Hong Kong, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Zhaoyang,Chen, Junliang,Fu, Hongbo,et al. Text2Face: Text-Based Face Generation With Geometry and Appearance Control[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2024,30(9):6481-6492.
APA Zhang, Zhaoyang,Chen, Junliang,Fu, Hongbo,Zhao, Jianjun,Chen, Shu-Yu,&Gao, Lin.(2024).Text2Face: Text-Based Face Generation With Geometry and Appearance Control.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,30(9),6481-6492.
MLA Zhang, Zhaoyang,et al."Text2Face: Text-Based Face Generation With Geometry and Appearance Control".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 30.9(2024):6481-6492.

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。