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

How to create "image-parse-new" when testing on custom images ? #37

Open farazkhanfk7 opened 3 years ago

farazkhanfk7 commented 3 years ago

I am testing CP-VTON+ on my custom images. I have created masks and parsed images for both cloth and models using some human-body parsing repos like CIHP, JPP-Net but couldn't understand the use of "image-parse-new" folder in test and train directories of VITON dataset. How to create these images inside "image-parse-new" folder. Nothing was mentioned about this in the README file.

minar09 commented 3 years ago

Please read this carefully: https://github.com/minar09/cp-vton-plus#data-preparation And this: https://github.com/minar09/cp-vton-plus#testing-with-custom-images Also, read our paper to understand the reason.

farazkhanfk7 commented 3 years ago

@minar09 Can you example of the script python dataset_neck_skin_correction.py for train and test directory ? How to run this with correct paths for train and test dir ?

minar09 commented 3 years ago

Defaults paths are already corrected. Just download the dataset and run the script.

tengolagan commented 1 year ago

what is the right palette color and the labels to set for creating parsed images like the ones from the folder image-parse-new ?

tengolagan commented 1 year ago

what is the right palette color and the labels to set for creating parsed images like the ones from the folder image-parse-new ?

(black and grey images)