unexpected glasses on restored images #235

Open
opened 2026-01-29 21:45:56 +00:00 by claunia · 0 comments
Owner

Originally created by @chky on GitHub (Aug 24, 2022).

great job!

The performance is quite good on many blurred face images, however, when I test the inference code on other datasets, some unexpected glasses emerge on restored image. Is there any parameters I can adjust to avoid this situation or I have to retrain the model on my dataset? I have loaded model v1.3 and some examples are as follows,
1
2
3

Thank you.

Originally created by @chky on GitHub (Aug 24, 2022). great job! The performance is quite good on many blurred face images, however, when I test the inference code on other datasets, some unexpected glasses emerge on restored image. Is there any parameters I can adjust to avoid this situation or I have to retrain the model on my dataset? I have loaded model v1.3 and some examples are as follows, ![1](https://user-images.githubusercontent.com/33181792/186373780-bcf78198-67a3-4e0d-b016-a841dbaee1b4.png) ![2](https://user-images.githubusercontent.com/33181792/186373791-ee58b333-59e1-4dbe-9952-474a10907468.png) ![3](https://user-images.githubusercontent.com/33181792/186373796-674f441b-9f44-43fc-9e51-eaf8eabb1207.png) Thank you.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: TencentARC/GFPGAN#235