GaFET: Learning Geometry-aware Facial Expression Translation from In-The-Wild Images | |
Tianxiang Ma1,2![]() ![]() ![]() | |
2023 | |
会议名称 | International Conference on Computer Vision |
会议日期 | 10.2-10.6 |
会议地点 | 法国巴黎 |
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. |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/56658 |
专题 | 模式识别实验室 |
通讯作者 | Jing Dong |
作者单位 | 1.School of Artificial Intelligence, UCAS 2.CRIPAC & NLPR, CASIA 3.ByteDance Ltd, Beijing, China 4.Nanjing University |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
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],2023. |
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 | ||
GaFET-+Learning+Geom(7315KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论