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
343 stars 120 forks source link

Is there any code to generate person image-mask? #76

Closed Sumukh0512 closed 3 years ago

Sumukh0512 commented 3 years ago

@minar09 I am building an interface for the cp-viton plus based virtual try-on project and I need code for generating image-mask. Can you guide me?

minar09 commented 3 years ago

@Sumukh0512, you can make image-mask by converting the image-parse into binary masks, or you can make use of the masking code from here: https://github.com/minar09/Clothing-Matching

Sumukh0512 commented 3 years ago

@minar09
Screenshot from 2021-06-26 17-49-32 Thanks for the reply. I am giving image-parse as input for cloth_masking_thresholding.py . How am I supposed to get the image-mask? I need your help.

Sumukh0512 commented 3 years ago

Screenshot from 2021-06-26 17-56-08 This is the output . Why is it completely white? Same code I am able to get output for cloth-mask but not for image-mask should I make any changes to the code?

minar09 commented 3 years ago

@Sumukh0512 , you can use the body_binary_masking.py from old commits (https://github.com/minar09/cp-vton-plus/blob/fcf29a512388881041ba84a97a43edfd1531cc38/body_binary_masking.py), although I removed it from current commits as it was making confusions. Thanks.

Sumukh0512 commented 3 years ago

@minar09 thanks