Towards effective learning for face super-resolution with shape and pose perturbations

doi:10.1016/j.knosys.2021.106938

	Towards effective learning for face super-resolution with shape and pose perturbations
	Hu, Xiyuan 1; Fan, Zhenfeng 2; Jia, Xu 3; Li, Zhihui 4; Zhang, Xuyun 5; Qi, Lianyong 6; Xuan, Zuxing 7
	2021-05-23
发表期刊	KNOWLEDGE-BASED SYSTEMS
ISSN	0950-7051
卷号	220 页码:10
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
关键词	Convolutional neural networks Face super-resolution Facial landmarks 3D face model
DOI	10.1016/j.knosys.2021.106938
收录类别	SCI
语种	英语
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
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000637680300016
出版者	ELSEVIER
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/16652
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.