csjliang / DASR

Official implementation of the paper 'Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution' in ECCV 2022
Apache License 2.0
128 stars 9 forks source link

testing datasets #9

Closed Lucien66 closed 2 years ago

Lucien66 commented 2 years ago

Hi, thank you for your work! will testing image degradation code be published in the future?

csjliang commented 2 years ago

Hi, thanks for your attention to our work.

Do you mean the code for preparing the synthetic testing dataset?

Lucien66 commented 2 years ago

yes!Is it possible for you to post the code for preparing testing dataset? Is there any reason why you haven't test on datasets such as set5 and set14?

csjliang commented 2 years ago

I have uploaded the code for preparing the dataset, please check (in DASR/scripts). We have tested the performance on the Urban100 dataset, which shows similar observations to the results of DIV2K (We did not report the results for readability). You can synthetic the validation data and test the DASR by yourself if you are interested. Thanks.