Facial image super-resolution guided by adaptive geometric features
文献类型：期刊论文
| 作者 | Fan,Zhenfeng1,2; Hu,Xiyuan1,2; Chen,Chen2; Wang,Xiaolian2; Peng,Silong2; Fan, Zhenfeng ; Hu, Xiyuan; Peng, Silong; Chen, Chen; Wang, Xiaolian
|
| 刊名 | EURASIP Journal on Wireless Communications and Networking
 |
| 出版日期 | 2020-07-17 |
| 卷号 | 2020期号:1 |
| 关键词 | Convolutional neural networks (CNNs) Depth map Face super-resolution |
| DOI | 10.1186/s13638-020-01760-y |
| 通讯作者 | Hu,Xiyuan(xiyuan.hu@ia.ac.cn) |
| 英文摘要 | AbstractThis paper addresses the traditional issue of restoring a high-resolution (HR) facial image from a low-resolution (LR) counterpart. Current state-of-the-art super-resolution (SR) methods commonly adopt the convolutional neural networks to learn a non-linear complex mapping between paired LR and HR images. They discriminate local patterns expressed by the neighboring pixels along the planar directions but ignore the intrinsic 3D proximity including the depth map. As a special case of general images, the face has limited geometric variations, which we believe that the relevant depth map can be learned and used to guide the face SR task. Motivated by it, we design a network including two branches: one for auxiliary depth map estimation and the other for the main SR task. Adaptive geometric features are further learned from the depth map and used to modulate the mid-level features of the SR branch. The whole network is implemented in an end-to-end trainable manner under the extra supervision of depth map. The supervisory depth map is either a paired one from RGB-D scans or a reconstructed one by a 3D prior model of faces. The experiments demonstrate the effectiveness of the proposed method and achieve improved performance over the state of the arts. |
| 语种 | 英语 |
| WOS记录号 | BMC:10.1186/S13638-020-01760-Y |
| 出版者 | Springer International Publishing |
| 源URL | [http://ir.ia.ac.cn/handle/173211/40132]  |
| 专题 | 自动化研究所_智能制造技术与系统研究中心_多维数据分析团队 |
| 通讯作者 | Hu,Xiyuan; Hu, Xiyuan |
| 作者单位 | 1.University of Chinese Academy of Sciences 2.Institute of Automation, Chinese Academy of Sciences |
| 推荐引用方式 GB/T 7714 | Fan,Zhenfeng,Hu,Xiyuan,Chen,Chen,et al. Facial image super-resolution guided by adaptive geometric features[J]. EURASIP Journal on Wireless Communications and Networking,2020,2020(1). |
| APA | Fan,Zhenfeng.,Hu,Xiyuan.,Chen,Chen.,Wang,Xiaolian.,Peng,Silong.,...&Wang, Xiaolian.(2020).Facial image super-resolution guided by adaptive geometric features.EURASIP Journal on Wireless Communications and Networking,2020(1). |
| MLA | Fan,Zhenfeng,et al."Facial image super-resolution guided by adaptive geometric features".EURASIP Journal on Wireless Communications and Networking 2020.1(2020). |
入库方式： OAI收割
来源：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。