TY - GEN
T1 - Face Super Resolution for VLQ facial images via parent patch matching
AU - Chen, Liang
AU - Hu, Ruimin
AU - Han, Zhen
AU - Wang, Zhongyuan
AU - Li, Qing
AU - Lu, Zheng
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/10/31
Y1 - 2016/10/31
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 Very Low Quality(VLQ), 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 use the target patch as well as the surrounding pixels, which we called parent patch, to represent the target patch. By incorporating the peripheral information, the parent patch is much more robust to noise in the LR and HR consistency learning. 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 Very Low Quality(VLQ), 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 use the target patch as well as the surrounding pixels, which we called parent patch, to represent the target patch. By incorporating the peripheral information, the parent patch is much more robust to noise in the LR and HR consistency learning. The effectiveness of proposed method is verified both quantitatively and qualitatively.
UR - http://www.scopus.com/inward/record.url?scp=85007227098&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2016.7727512
DO - 10.1109/IJCNN.2016.7727512
M3 - Conference contribution
AN - SCOPUS:85007227098
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 2515
EP - 2521
BT - 2016 International Joint Conference on Neural Networks, IJCNN 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 International Joint Conference on Neural Networks, IJCNN 2016
Y2 - 24 July 2016 through 29 July 2016
ER -