search

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
355 stars 122 forks source link

output human face blurry ,any suggestions? #70

Closed Apokar closed 3 years ago

Apokar commented 3 years ago

Thank you for the excellent work, I found the output clothes basically fit character but the characters' faces became blurry, any suggestions?

RESULT: 1 (2)

Here is data :

-- cloth 3

-- cloth-mask 3

-- image 1

-- image-mask 1

-- image-parse 1

-- image-parse-new 1

-- warp-cloth 1

-- warp-mask 1

minar09 commented 3 years ago

Hi @Apokar , are all of your output have blurry faces or just this? If it affects all, maybe you can debug the network more closely, looks like TOM network input is missing the im_head or something, not very sure though. Hope you can find it out. Good luck.

Apokar commented 3 years ago

Hi @Apokar , are all of your output have blurry faces or just this? If it affects all, maybe you can debug the network more closely, looks like TOM network input is missing the im_head or something, not very sure though. Hope you can find it out. Good luck.

Haha,I misplaced the pictures in two folders. image-parse image-parse-new Thx ur reply!

omaraga12 commented 2 years ago

@Apokar can you explain how did you give solution to it? I have the same problem image image

kukuhaza commented 2 years ago

I have face blurry problem too, how to solve this?