DeMeshNet: Blind Face Inpainting for Deep MeshFace Veriﬁcation

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	DeMeshNet: Blind Face Inpainting for Deep MeshFace Veriﬁcation
	Shu Zhang1 ; Ran He1,2 ; Zhenan Sun1,2 ; Tieniu Tan1,2
刊名	IEEE Transactions on Information Forensics and Security
	2018-03
卷号	13 期号:3 页码:637-647
关键词	Meshface Face Verification Blind Inpainting Deep Learning Demeshnet Spatial Transformer
英文摘要	MeshFace photos have been widely used in many Chinese business organizations to protect ID face photos from being misused. The occlusions incurred by random meshes severely degenerate the performance of face verification systems, which raises the MeshFace verification problem between MeshFace and daily photos. Previous methods cast this problem as a typical low-level vision problem, i.e., blind inpainting. They recover perceptually pleasing clear ID photos from MeshFaces by enforcing pixel level similarity between the recovered ID images and the ground-truth clear ID images and then perform face verification on them. Essentially, face verification is conducted on a compact feature space rather than the image pixel space. Therefore, this paper argues that pixel level similarity and feature level similarity jointly offer the key to improve the verification performance. Based on this insight, we offer a novel feature oriented blind face inpainting framework. Specifically, we implement this by establishing a novel DeMeshNet, which consists of three parts. The first part addresses blind inpainting of the MeshFaces by implicitly exploiting extra supervision from the occlusion position to enforce pixel level similarity. The second part explicitly enforces a feature level similarity in the compact feature space, which can explore informative supervision from the feature space to produce better inpainting results for verification. The last part copes with face alignment within the net via a customized spatial transformer module when extracting deep facial features. All three parts are implemented within an end-to-end network that facilitates efficient optimization. Extensive experiments on two MeshFace data sets demonstrate the effectiveness of the proposed DeMeshNet as well as the insight of this paper.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/19704]
专题	自动化研究所_智能感知与计算研究中心
通讯作者	Ran He
作者单位	1.Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences
推荐引用方式 GB/T 7714	Shu Zhang,Ran He,Zhenan Sun,et al. DeMeshNet: Blind Face Inpainting for Deep MeshFace Veriﬁcation[J]. IEEE Transactions on Information Forensics and Security,2018,13(3):637-647.
APA	Shu Zhang,Ran He,Zhenan Sun,&Tieniu Tan.(2018).DeMeshNet: Blind Face Inpainting for Deep MeshFace Veriﬁcation.IEEE Transactions on Information Forensics and Security,13(3),637-647.
MLA	Shu Zhang,et al."DeMeshNet: Blind Face Inpainting for Deep MeshFace Veriﬁcation".IEEE Transactions on Information Forensics and Security 13.3(2018):637-647.