中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Towards effective learning for face super-resolution with shape and pose perturbations

文献类型：期刊论文

作者Hu, Xiyuan1; Fan, Zhenfeng2; Jia, Xu3; Li, Zhihui4; Zhang, Xuyun5; Qi, Lianyong6; Xuan, Zuxing7
刊名KNOWLEDGE-BASED SYSTEMS
出版日期2021-05-23
卷号220页码:10
关键词Convolutional neural networks Face super-resolution Facial landmarks 3D face model
ISSN号0950-7051
DOI10.1016/j.knosys.2021.106938
英文摘要Recent development of convolutional neural networks (CNNs) has activated a lot of studies and boosted the performance greatly on image super-resolution. This paper addresses the issue of face super-resolution, which attracts a lot of interests in the photographic industry. We propose to make use of the face-specific priors to enhance the performance of face super-resolution with the convolutional neural networks. Classical facial prior models represent the 2D facial shape in a compact low-dimensional space expressed by principal components. Here, we impose perturbations on the low dimensional space and generate face samples with novel appearance. First, we conduct 2D facial image perturbations through 2D facial landmarks. Then, we carry on the study with perturbations on 3D facial landmarks. Facial pose and shape are perturbated to generate novel appearances of a single 2D facial image. These novel facial samples are then fed into the training process of the convolutional neural networks for face super-resolution. The experimental results demonstrate that the proposed method is adaptable to various networks and achieves superior performance for the face super-resolution task. (c) 2021 Published by Elsevier B.V. Superscript/Subscript Available
资助项目Beijing outstanding talents training fund for youth top individual and Premium Funding Project for Academic Human Resources Development in Beijing Union University[BPHR2020EZ01]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000637680300016
出版者ELSEVIER
源URL[http://119.78.100.204/handle/2XEOYT63/16651]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Xuan, Zuxing
作者单位1.Nanjing Univ Sci & Technol, Sch Comp Sci & Technol, Nanjing, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
3.Huawei Noahs Ark Lab, Beijing, Peoples R China
4.MPS, Inst Forens Sci, Beijing, Peoples R China
5.Macquarie Univ, Dept Comp, Sydney, NSW 2109, Australia
6.Qufu Normal Univ, Sch Comp Sci, Qufu, Shandong, Peoples R China
7.Beijing Union Univ, Inst Fundamental & Interdisciplinary Sci, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Hu, Xiyuan,Fan, Zhenfeng,Jia, Xu,et al. Towards effective learning for face super-resolution with shape and pose perturbations[J]. KNOWLEDGE-BASED SYSTEMS,2021,220:10.
APA Hu, Xiyuan.,Fan, Zhenfeng.,Jia, Xu.,Li, Zhihui.,Zhang, Xuyun.,...&Xuan, Zuxing.(2021).Towards effective learning for face super-resolution with shape and pose perturbations.KNOWLEDGE-BASED SYSTEMS,220,10.
MLA Hu, Xiyuan,et al."Towards effective learning for face super-resolution with shape and pose perturbations".KNOWLEDGE-BASED SYSTEMS 220(2021):10.

入库方式： OAI收割

来源：计算技术研究所

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。