/ACGPN

"Towards Photo-Realistic Virtual Try-On by Adaptively Generating↔Preserving Image Content",CVPR 2020. (Modified from original with fixes for inference)

Primary LanguagePython

Original README

Disclaimer

This is just a slightly modified repository of DeepFashion_Try_On (ACGPN) for inference and visualization. Please refer to the original repository for details.

Towards Photo-Realistic Virtual Try-On by Adaptively Generating↔Preserving Image Content, CVPR'20.

Official code for CVPR 2020 paper 'Towards Photo-Realistic Virtual Try-On by Adaptively Generating↔Preserving Image Content'. We rearrange the VITON dataset for easy access.

[Dataset Partition Label] [Sample Try-on Video] [Checkpoints]

[Dataset_Test] [Dataset_Train]

[Paper]

Inference

  1. Download the test dataset and unzip
  2. Download the checkpoints and unzip
  3. Then run - python test.py

Dataset Partition We present a criterion to introduce the difficulty of try-on for a certain reference image.

The specific key points we choose to evaluate the try-on difficulty

image

Segmentation Label

0 -> Background
1 -> Hair
4 -> Upclothes
5 -> Left-shoe 
6 -> Right-shoe
7 -> Noise
8 -> Pants
9 -> Left_leg
10 -> Right_leg
11 -> Left_arm
12 -> Face
13 -> Right_arm

Sample images from different difficulty level

image

Sample Try-on Results

image

Training Details

For better inference performance, model G and G2 should be trained with 200 epoches, while model G1 and U net should be trained with 20 epoches.

License

The use of this software is RESTRICTED to non-commercial research and educational purposes.

Citation

If you use our code or models in your research, please cite with:

@InProceedings{Yang_2020_CVPR,
author = {Yang, Han and Zhang, Ruimao and Guo, Xiaobao and Liu, Wei and Zuo, Wangmeng and Luo, Ping},
title = {Towards Photo-Realistic Virtual Try-On by Adaptively Generating-Preserving Image Content},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}

Dataset

VITON Dataset This dataset is presented in VITON, containing 19,000 image pairs, each of which includes a front-view woman image and a top clothing image. After removing the invalid image pairs, it yields 16,253 pairs, further splitting into a training set of 14,221 paris and a testing set of 2,032 pairs.