LDL
LDL copied to clipboard
Official implementation of the paper 'Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution' in CVPR 2022
I get the "Imaginary component" error when I try to evaluate the FID on Set5 dataset. I firstly use "scripts/metrics/table_calculate_fid_stats_from_datasets.py" to generate the stats for Set5. Then I use the...
Hi, Can you provide the code for generating local residual variation map (A map like the 4th column of Figure 5 in the paper)? Thank you!
不知道是因为训练数据的原因还是啥,让我感觉这个在文字复原上效果比较差,超分之后的比较差,而且不太适用与高倍超分,或许是还未看懂论文
Hello, in the testset links you provided, there are only 13 pictures in Set14.
Thanks for your work, can you provide the yml files of SRGAN/MSRResNet used for training and testing?
Could implement Demo Real Esrgan + ldl in Google Colab. Thank you.
When I train on the face dataset, the teeth have a weird phenomenon。The portrait dataset is FFHQ, and the teeth generated by super-resolution are divided into multiple tooth blocks. May...
Hi, your proposed LDL is a great approach in the field of SR and I would like to reproduce your findings.
Obviously, BasicSR is a good tool. However It is true that BasicSR is easy to use, but when I try to apply it, it takes too long to find out...
The error in the training process seems to be a data problem,but i can not find any reason.There is nothing wrong with the data.There is an error in the middle...