Why parse_head is not the same in GMM and TOM stage?

minar09 / cp-vton-plus

Official implementation for "CP-VTON+: Clothing Shape and Texture Preserving Image-Based Virtual Try-On", CVPRW 2020

https://minar09.github.io/cpvtonplus/

MIT License

346 stars 120 forks source link

Why parse_head is not the same in GMM and TOM stage? #62

Closed VVingerfly closed 3 years ago

VVingerfly commented 3 years ago

Hi, @minar09 @thaithanhtuan thanks for the great work!

I was wondering why parse_head is different in GMM and TOM stage, shouldn't they be the same?

https://github.com/minar09/cp-vton-plus/blob/916d7337703b49e18c8005f4b1847ba53c76c9e9/cp_dataset.py#L110-L124

B.R.

minar09 commented 3 years ago

Hi @VVingerfly , actually that is one of the contributions of CP-VTON+. By using a different parse_head for GMM, we can preserve the original clothing shape around the neck. Please feel free to read the paper for more details. Thank you.

VVingerfly commented 3 years ago

Got it, thanks for your reply. Closing this issue now :-)