Closed CongHuang96 closed 2 years ago
We follow the test paradigm of Kind and Kind++ which use mean_gt to fine-tune the overall brightness.
For other competitors which may be greatly affected by the overall brightness, e.g., Zero-DCE, we also fine-tune their overall brightness and report their better results for fair comparison.
Hi,in code/test.py line 148, you use the mean_gt to fine-tune the overall brightness.
Is it fair to compare with other methods? MIRNet does not fine-tune the brightness.