Guangyang Wu

Guangyang Wu

Auto-generated profile, based on publicly available information

Guangyang Wu

Shanghai Jiao Tong University, Shanghai, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 October 2023
Verified
Conference Paper
Open access
WLWenhao Li
Wenhao Li
GWGuangyang Wu
Guangyang Wu
WWWenyi Wang
Wenyi Wang
PRPeiran Ren
Peiran Ren
XLXiaohong Liu
Xiaohong Liu

14 April 2020 in IEEE Access
Verified
Journal Article
Open access
WWWenyi Wang
Wenyi Wang
GWGuangyang Wu
Guangyang Wu
WCWeitong Cai
Weitong Cai
LZLiaoyuan Zeng
Liaoyuan Zeng
JCJianwen Chen
Jianwen Chen
Although SISR (Single Image Super Resolution) problem can be effectively solved by deep learning based methods, the training phase often considers single degradation type such as bicubic interpolation or Gaussian blur with fixed variance. These priori hypotheses often fail and lead to reconstruction error in real scenario. In this paper, we propose an end-to-end CNN model RPSRMD to handle SR problem in multiple Gaussian degradations by extracting and using as side information a shared image prior that is consistent in different Gaussian degradations. The shared image prior is generated by an AED network RPGen with a rationally designed loss function that contains two parts: consistency loss and validity loss. These losses supervise the training of AED to guarantee that the image priors of one image with different Gaussian blurs to be very similar. Afterwards we carefully designed a SR network, which is termed as PResNet (Prior based Residual Network) in this paper, to efficiently use the image priors and generate high quality and robust SR images when unknown Gaussian blur is presented. When we applied variant Gaussian blurs to the low resolution images, the experiments prove that our proposed RPSRMD, which includes RPGen and PResNet as two core components, is superior to many state-of-the-art SR methods that were designed and trained to handle multi-degradation.