deepinsight / deepinsight/insightface
face swapper results are different (more accurate) when using darker target image
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
This is something I have discovered accidentally.
Source---------------------------------------Target-----------------------------------------Result
When I am making the target image darker (second set) by reducing it's gamma, the resulting image is more similar to the source image. How do I can achieve the similar features without reducing the gamma of target image?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.