Cosmetic-Aware Makeup Cleanser | |
Li, Yi1,2,3![]() ![]() ![]() ![]() | |
2019-09 | |
会议名称 | IEEE International Conference on Biometrics: Theory, Applications and Systems |
会议日期 | 23-26 September 2019 |
会议地点 | Tampa, Florida, USA |
摘要 | Face verification aims at determining whether a pair of face images belongs to the same identity. Recent studies have revealed the negative impact of facial makeup on the verification performance. With the rapid development of deep generative models, this paper proposes a semanticaware makeup cleanser (SAMC) to remove facial makeup under different poses and expressions and achieve verification via generation. The intuition lies in the fact that makeup is a combined effect of multiple cosmetics and tailored treatments should be imposed on different cosmetic regions. To this end, we present both unsupervised and supervised semantic-aware learning strategies in SAMC. At image level, an unsupervised attention module is jointly learned with the generator to locate cosmetic regions and estimate the degree. At feature level, we resort to the effort of face parsing merely in training phase and design a localized texture loss to serve complements and pursue superior synthetic quality. The experimental results on four makeuprelated datasets verify that SAMC not only produces appealing de-makeup outputs at a resolution of 256256, but also facilitates makeup-invariant face verification through image generation. |
七大方向——子方向分类 | 图像视频处理与分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39177 |
专题 | 模式识别实验室 |
通讯作者 | He, Ran |
作者单位 | 1.CRIPAC, National Laboratory of Pattern Recognition, CASIA 2.Center for Excellence in Brain Science and Intelligence Technology, CAS 3.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li, Yi,Huang, Huaibo,Yu, Junchi,et al. Cosmetic-Aware Makeup Cleanser[C],2019. |
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 | ||
0007.pdf(3098KB) | 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