search

switchablenorms / CelebAMask-HQ

A large-scale face dataset for face parsing, recognition, generation and editing.
2.05k stars 343 forks source link

Hi ! how to get the ground-true masks of some other datasets? #38

Closed wqz960 closed 4 years ago

wqz960 commented 4 years ago

Thank you for your wonderful codes and dataset!!! how is ground-true masks of HQ dataset produced? artificial annotation or annotated by some segmentation network? The GAN-demo project seems that the GAN is used to transform the label to synthesis images. In the face-parsing project, the result seems bad especially for the large-pose face, can you tell me how the ground-true masks produced or can you introduce me some GAN to produce the masks. I am very sorry for my bad English! Looking forward for your respond! Thank you!

steven413d commented 4 years ago

Hi,

Thanks for your interest in our project! Ground-true masks are produced by human annotation. For poor results in face parsing, you can try other state-of-the-art parsing models to solve the problem because our released model is a baseline.