TY - GEN
T1 - A joint learning based Face Super Resolution approach via contextual topological structure
AU - Chen, Liang
AU - Hu, Ruimin
AU - Han, Zhen
AU - Wang, Zhongyuan
AU - Li, Qing
PY - 2017/6/16
Y1 - 2017/6/16
N2 - Face Super Resolution(FSR) is to infer High Resolution(HR) facial images from given Low Resolution(LR) ones with the assistance of LR and HR training pairs. Among existing methods, local patch based methods are superior in visual and objective quality than global based methods. These local patch based methods are based on the consistency assumption that the neighbors in HR/LR space form similar local geometry. But when LR images are with low quality, the LR space is seriously contaminated that even two distinct patches look similar, which means that the consistency assumption is not well held anymore. To this end, in this paper we introduce the contextual topological structure of target patch to improve the consistency. The contextual topological structure consists of the target patch as well as its adjacent patches, we explore the relationship between them based on statistical probability and apply the relationship for joint learning progress of mapping from LR to HR. By incorporating the contextual topological structure, the robustness to noise of approach is increased as well as the LR/HR consistency. The effectiveness of proposed method is verified both quantitatively and qualitatively.
AB - Face Super Resolution(FSR) is to infer High Resolution(HR) facial images from given Low Resolution(LR) ones with the assistance of LR and HR training pairs. Among existing methods, local patch based methods are superior in visual and objective quality than global based methods. These local patch based methods are based on the consistency assumption that the neighbors in HR/LR space form similar local geometry. But when LR images are with low quality, the LR space is seriously contaminated that even two distinct patches look similar, which means that the consistency assumption is not well held anymore. To this end, in this paper we introduce the contextual topological structure of target patch to improve the consistency. The contextual topological structure consists of the target patch as well as its adjacent patches, we explore the relationship between them based on statistical probability and apply the relationship for joint learning progress of mapping from LR to HR. By incorporating the contextual topological structure, the robustness to noise of approach is increased as well as the LR/HR consistency. The effectiveness of proposed method is verified both quantitatively and qualitatively.
KW - consistency enhancement
KW - contextual topological structure
KW - face super resolution
KW - low level vision
UR - http://www.scopus.com/inward/record.url?scp=85023758390&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2017.7952324
DO - 10.1109/ICASSP.2017.7952324
M3 - Conference article published in proceeding or book
AN - SCOPUS:85023758390
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 1088
EP - 1092
BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
Y2 - 5 March 2017 through 9 March 2017
ER -