GaFET: Learning Geometry-aware Facial Expression Translation from In-The-Wild Images
文献类型:会议论文
作者 | Tianxiang Ma1,3![]() ![]() ![]() |
出版日期 | 2023 |
会议日期 | 10.2-10.6 |
会议地点 | 法国巴黎 |
英文摘要 | While current face animation methods can manipulate expressions individually, they suffer from several limitations. The expressions manipulated by some motion-based facial reenactment models are crude. Other ideas modeled with facial action units cannot generalize to arbitrary expressions not covered by annotations. In this paper, we introduce a novel Geometry-aware Facial Expression Translation (GaFET) framework, which is based on parametric 3D facial representations and can stably decoupled expression. Among them, a Multi-level Feature Aligned Transformer is proposed to complement non-geometric facial detail features while addressing the alignment challenge of spatial features. Further, we design a De-expression model based on StyleGAN, in order to reduce the learning difficulty of GaFET in unpaired “in-the-wild” images. Extensive qualitative and quantitative experiments demonstrate that we achieve higher-quality and more accurate facial expression transfer results compared to state-of-the-art methods, and demonstrate applicability of various poses and complex textures. Besides, videos or annotated training data are omitted, making our method easier to use and generalize. |
源URL | [http://ir.ia.ac.cn/handle/173211/56658] ![]() |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | Jing Dong |
作者单位 | 1.School of Artificial Intelligence, UCAS 2.Nanjing University 3.CRIPAC & NLPR, CASIA 4.ByteDance Ltd, Beijing, China |
推荐引用方式 GB/T 7714 | Tianxiang Ma,Bingchuan Li,Qian He,et al. GaFET: Learning Geometry-aware Facial Expression Translation from In-The-Wild Images[C]. 见:. 法国巴黎. 10.2-10.6. |
入库方式: OAI收割
来源:自动化研究所
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。