Learning disentangling and fusing networks for face completion under structured occlusions | |
Li ZH(李志航)1,2,3,4![]() ![]() ![]() | |
发表期刊 | Pattern Recognition
![]() |
2020 | |
卷号 | 99期号:1页码:107073 |
摘要 | Face completion aims to generate semantically new pixels for missing facial components. It is a challeng- ing generative task due to large variations of face appearance. This paper studies generative face com- pletion under structured occlusions. We treat the face completion and corruption as disentangling and fusing processes of clean faces and occlusions, and propose a jointly disentangling and fusing Generative Adversarial Network (DF-GAN). First, three domains are constructed, corresponding to the distributions of occluded faces, clean faces and structured occlusions. The disentangling and fusing processes are formu- lated as the transformations between the three domains. Then the disentangling and fusing networks are built to learn the transformations from unpaired data, where the encoder-decoder structure is adopted and allows DF-GAN to simulate structure occlusions by modifying the latent representations. Finally, the disentangling and fusing processes are unified into a dual learning framework along with an adversarial strategy. The proposed method is evaluated on Meshface verification problem. Experimental results on four Meshface databases demonstrate the effectiveness of our proposed method for the face completion under structured occlusions. |
关键词 | face completion |
语种 | 英语 |
七大方向——子方向分类 | 图像视频处理与分析 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44401 |
专题 | 模式识别实验室 |
通讯作者 | He R(赫然) |
作者单位 | 1.National Laboratory of Pattern Recognition, CASIA, China 2.Center for Excellence in Brain Science and Intelligence Technology, CAS, China 3.University of Chinese Academy of Sciences, Beijing, 100049, China 4.Center for Research on Intelligent Perception and Computing, CASIA, China |
第一作者单位 | 中国科学院自动化研究所; 模式识别国家重点实验室 |
通讯作者单位 | 中国科学院自动化研究所; 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Li ZH,Hu YB,He R,et al. Learning disentangling and fusing networks for face completion under structured occlusions[J]. Pattern Recognition,2020,99(1):107073. |
APA | Li ZH,Hu YB,He R,&Sun ZN.(2020).Learning disentangling and fusing networks for face completion under structured occlusions.Pattern Recognition,99(1),107073. |
MLA | Li ZH,et al."Learning disentangling and fusing networks for face completion under structured occlusions".Pattern Recognition 99.1(2020):107073. |
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 | ||
PR.pdf(3949KB) | 期刊论文 | 作者接受稿 | 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