Face hallucination from low quality images using definition-scalable inference. (October 2019)

• Record Type: Journal Article
• Authors: Hu, Xiao; Ma, Peirong; Mai, Zhuohao; Peng, Shaohu; Yang, Zhao; Wang, Li
• Is Part Of: Pattern recognition. Volume 94(2019:Oct.)
• Page Start: 110
• Page End: 121
• Publication Date: 2019-10
• Subjects: SIFT -- PCA -- Sparse representation -- Deep learning -- Generative adversarial networks; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.05.027
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A method is introduced to hallucinate super-low face from real low-quality face instead of stimulated low-quality face. A definition-scalable strategy: a face is decomposed into a basic face with low-definition and an enhanced face with high-frequency information. The super-resolution technique based on definition-scalable inference effectively estimate structural information and high-frequency texture from real low-res faces. The matched SIFT key-points is proposed to estimate the similarity of the super-res face and its high-res labeled face. The proposed SISR method can recover more structure information and local information from real low-quality face and more SIFT key-points than the state of the arts. Abstract: To hallucinate super-resolution ( super-res ) face from a real low-quality face, a super-resolution technique based on definition-scalable inference (SRDSI) is proposed in this paper. In the proposed strategy, all high-res labeled faces are first decomposed into basic faces and enhanced faces to train a basic face and an enhanced face inferring model, and then two inferring models are used to hallucinate super-res basic face with low-definition and enhanced faces with high-frequency information from a single low-res face. Finally, the basic face is merged with its enhanced face into a super-res face with high-definition. In addition, this paper employs SIFT key-points to evaluate the similarity between the super-res face and its high-res labeled face. Experimental results show that SRDSI can effectively recover more structural information as well as SIFT key-points from real low-res faces and achieves better performance than state-of-the-art super-resolution techniques in terms of both visual and objective quality. Graphicalabstracts : Image, graphical abstract