Laplacian pyramid adversarial network for face completion
文献类型：期刊论文
| 作者 | Cong Y(丛杨)2 ; Tang YD(唐延东)2; Wang Q(王强)1,2; Fan HJ(范慧杰)2; Sun G(孙干)1,2
|
| 刊名 | Pattern Recognition
 |
| 出版日期 | 2019 |
| 卷号 | 88页码:493-505 |
| 关键词 | Face completion Generative adversarial network Laplacian pyramid |
| ISSN号 | 0031-3203 |
| 产权排序 | 1 |
| 英文摘要 | Recently, generative adversarial networks (GANs) have demonstrated high-quality reconstruction in face completion. There is still much room for improvement over the conventional GAN models that do not explicitly address the texture details problem. In this paper, we propose a Laplacian-pyramid-based generative framework for face completion. This framework can produce more realistic results (1) by deriving precise content information of missing face regions in a coarse-to-fine fashion and (2) by propagating the high-frequency details from the surrounding area via a modified residual learning model. Specifically, for the missing regions, we design a Laplacian-pyramid-based convolutional network framework that can predict missing regions under different resolutions; this framework takes advantage of multiscale features shared from low levels and extracted from middle layers for the next finer level. For high-frequency details, we construct a new residual learning network to eliminate color discrepancies between the missing and surrounding regions progressively. Furthermore, a multiloss function is proposed to supervise the generative process. To optimize the model, we train the entire generative model with deep supervision using a joint reconstruction loss, which ensures that the generated image is as realistic as the original. Extensive experiments on benchmark datasets show that the proposed framework exhibits superior performance over state-of-the-art methods in terms of predictive accuracy, both quantitatively and qualitatively. |
| 资助项目 | National Natural Science Foundation of China[61873259] ; National Natural Science Foundation of China[61333019] ; National Natural Science Foundation of China[U1613214] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000457666900039 |
| 资助机构 | National Natural Science Foundation of China |
| 源URL | [http://ir.sia.cn/handle/173321/23870]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 通讯作者 | Fan HJ(范慧杰) |
| 作者单位 | 1.University of Chinese Academy of Sciences, Beijing 100049, China 2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110016, China |
| 推荐引用方式 GB/T 7714 | Cong Y,Tang YD,Wang Q,et al. Laplacian pyramid adversarial network for face completion[J]. Pattern Recognition,2019,88:493-505. |
| APA | Cong Y,Tang YD,Wang Q,Fan HJ,&Sun G.(2019).Laplacian pyramid adversarial network for face completion.Pattern Recognition,88,493-505. |
| MLA | Cong Y,et al."Laplacian pyramid adversarial network for face completion".Pattern Recognition 88(2019):493-505. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
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。