Blind image super-resolution based on prior correction network
Blind image super-resolution based on prior correction network
复制标题
基于先验校正网络的盲图像超分辨率
DOI：
10.1016/j.neucom.2021.07.070
复制
发表时间：
2021
期刊：
影响因子：
6
通讯作者：
Tan Zehan
中科院分区：
文献类型：
--
作者：
Cao Xiang;Luo Yihao;Xiao Yi;Zhu Xianyi;Wang Tianjiang;Feng Qi;Tan Zehan
Convolutional neural networks (CNNs) based super-resolution (SR) methods have achieved remarkable progress in recent years. Most of these methods assume that the degradation is known and fixed, such as bicubic downsampling. However, the performance of CNNs-based methods suffers from a severe drop when the actual degradation mismatch the training one. This paper proposes a prior correction network (PCNet) to solve the blind SR problem, which makes CNNs-based super-resolvers trained in a fixed blur kernel but applied to other unknown blur kernels. The PCNet consists of a kernel estimation network, a correction filter module, and a correction refinement network. The kernel estimation network aims to estimate unknown blur kernel from the input low-resolution (LR) image. The correction filter module then transfers the estimated degraded domains to adapt to specific degradations (e.g., bicubic downsampling). Finally, the correction refinement network adjusts the corrected LR image to eliminate the influence of blur kernel mismatch or misestimate. Experimental results on diverse datasets show that the proposed PCNet, combined with existing CNNs-based SR methods, outperforms other state-of-the-art algorithms for blind SR. Code is available at: \url{https://github.com/caoxiang104/PCNet}.
登录
查看更多内容
影响因子：
6
作者：
Jinghui Chu;Xiaochuan Li;Jiaqi Zhang;W. Lu
通讯作者：
Jinghui Chu;Xiaochuan Li;Jiaqi Zhang;W. Lu
DOI：
10.1109/tcsvt.2020.2996592
发表时间：
2021-03
影响因子：
8.4
作者：
Liqin Huang;Youshen Xia
通讯作者：
Liqin Huang;Youshen Xia
DOI：
--
发表时间：
2019-09
期刊：
ArXiv
影响因子：
--
作者：
Sefi Bell-Kligler;Assaf Shocher;M. Irani
通讯作者：
Sefi Bell-Kligler;Assaf Shocher;M. Irani
影响因子：
6
作者：
Xiang Cao;Yihao Luo;Xianyi Zhu;Liangqi Zhang;Yan Xu;Haibo Shen;Tianjiang Wang;Qi Feng
通讯作者：
Xiang Cao;Yihao Luo;Xianyi Zhu;Liangqi Zhang;Yan Xu;Haibo Shen;Tianjiang Wang;Qi Feng
影响因子：
10.6
作者：
Jun Yu;Y. Rui;D. Tao
通讯作者：
Jun Yu;Y. Rui;D. Tao