This is an unofficial code replication for a paper titled, "Two-stage Network For Single Image Super-Resolution." However, there are some modifications to improve the results, specifically, the Sobel kernel-based loss function (Refer to the "dummy paper"). See the "Readme to run the code.txt" file to run the codes. If you find any error or deviation from the original paper let me know. If you use this code, don't forget to cite the original paper:
Y. Han, X. Du and Z. Yang, "Two-stage Network For Single Image Super-Resolution," 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Nashville, TN, USA, 2021, pp. 880-887, doi: 10.1109/CVPRW53098.2021.00098.
@inproceedings{Han2021, title = {Two-stage Network For Single Image Super-Resolution}, url = {http://dx.doi.org/10.1109/CVPRW53098.2021.00098}, DOI = {10.1109/cvprw53098.2021.00098}, booktitle = {2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)}, publisher = {IEEE}, author = {Han, Yuzhuo and Du, Xiaobiao and Yang, Zhi}, year = {2021}, month = jun }