SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfer | |
Yueming Lyu![]() ![]() ![]() ![]() | |
2021 | |
会议名称 | ACM International Conference on Multimedia |
会议日期 | 2021-10 |
会议地点 | Cheng du, China |
摘要 | In recent years, virtual makeup applications have become more and more popular. However, it is still challenging to propose a robust makeup transfer method in the real-world environment. Current makeup transfer methods mostly work well on good-conditioned clean makeup images, but transferring makeup that exhibits shadow and occlusion is not satisfying. To alleviate it, we propose a novel makeup transfer method, called 3D-Aware Shadow and Occlusion Robust GAN (SOGAN). Given the source and the reference faces, we first fit a 3D face model and then disentangle the faces into shape and texture. In the texture branch, we map the texture to the UV space and design a UV texture generator to transfer the makeup. Since human faces are symmetrical in the UV space, we can conveniently remove the undesired shadow and occlusion from the reference image by carefully designing a Flip Attention Module (FAM). After obtaining cleaner makeup features from the reference image, a Makeup Transfer Module (MTM) is introduced to perform accurate makeup transfer. The qualitative and quantitative experiments demonstrate that our SOGAN not only achieves superior results in shadow and occlusion situations but also performs well in large pose and expression variations. |
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/173211/56614 |
专题 | 模式识别实验室 |
通讯作者 | Jing Dong |
作者单位 | 1.Institute of Automation Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Yueming Lyu,Jing Dong,Bo Peng,et al. SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfer[C],2021. |
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 | ||
SOGAN.pdf(2943KB) | 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