search

sczhou / CodeFormer

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Other
15.43k stars 3.25k forks source link

Results not really good on close portraits #51

Open lazy-nurd opened 1 year ago

lazy-nurd commented 1 year ago

Hey @sczhou Thank you so much for this repo I have been waiting for training code, but you have said that it is delayed for some time. But codeformer performs really good in face restoration for images which are at a distance, but fails miserably for selfies and mostly people with glasses. It adds double eyebrows etc. So if you cannot release training code right now, then please train codeformer on more dataset which can make it robust on real faces and can be used as face restoration on general images.

sczhou commented 1 year ago

Thanks. We are planning to train a new CodeFormer model with less identity loss, but the downside is that the robustness may be weakened at a cost. You can also check out this discussion #9

lazy-nurd commented 1 year ago

@sczhou That will be perfect. When can we expect this to be released ?