GuoLanqing
commented
1 year ago Maybe you can try some unsupervised methods or use the adversarial loss to finetune the generator.
Open pengzhao-life opened 1 year ago
GuoLanqing
commented
1 year ago Maybe you can try some unsupervised methods or use the adversarial loss to finetune the generator.
Hi thank you for sharing such great work! I would like to fine tune the model on our data, but the ground truth i.e. shadow free images are not available in the non-lab environment. I wonder if any suggestions? Thanks!