Repository files navigation

Code and dataset for the CVPR 2018 paper "VITON: An Image-based Virtual Try-on Network"

The person representation used in this paper are extracted by a 2D pose estimator and a human parser:

• Realtime Multi-Person Pose Estimation
• Self-supervised Structure-sensitive Learning

Thanks@MosbehBarhoumi for creating aColab Notebook for quick preprocessing the data.

The dataset is no longer publicly available due to copyright issues. For thoese who have already downloaded the dataset, please note that using or distributing it is illegal!

Download pretrained models onGoogle Drive. Put them undermodel/ folder.

Runtest_stage1.sh to do the inference.The results are inresults/stage1/images/.results/stage1/index.html visualizes the results.

Run the matlab scriptshape_context_warp.m to extract the TPS transformation control points.

Thentest_stage2.sh will do the refinement and generate the final results, which locates inresults/stage2/images/.results/stage2/index.html visualizes the results.

Go insideprepare_data.

First runextract_tps.m. This will take sometime, you can try run it in parallel or directly download the pre-computed TPS control points via Google Drive and put them indata/tps/.

Then run./preprocess_viton.sh, and the generated TF records will be inprepare_data/tfrecord.

Runtrain_stage1.sh

Runtrain_stage2.sh

If this code or dataset helps your research, please cite our paper:

@inproceedings{han2017viton,  title = {VITON: An Image-based Virtual Try-on Network},  author = {Han, Xintong and Wu, Zuxuan and Wu, Zhe and Yu, Ruichi and Davis, Larry S},  booktitle = {CVPR},  year  = {2018},}