We provide visualization results of various state-of-the-art methods to facilitate your experimental comparisons.
Visualization results of CP-VTON, CP-VTON+, ClothFlow, ACGPN, PF-AFN, DCTON, RT-VTON and our DOC-VTON.
Model | Published | Code | FID |
---|---|---|---|
CP-VTON | ECCV2018 | Code | 24.43 |
CP-VTON+ | CVPRW2020 | Code | 21.08 |
ClothFlow | ICCV2019 | - | 14.43 |
ACGPN | CVPR2020 | Code | 15.67 |
DCTON | CVPR2021 | Code | 14.82 |
PF-AFN | CVPR2021 | Code | 10.09 |
RT-VTON | CVPR2022 | - | 11.66 |
DOC-VTON | TMM2023 | Code | 9.54 |
We provide densepose results of VITON test imgs.
We reprocess the densepose results and human parsing results of VITON-HD (Training and Testing dataset). You can download them through Baiduyun. PWD: deh8.
We recommend using PF-AFN as codebase, which contains tensorboard, DDP training set, and nice code.
Official Codes for OccluMix: Towards De-Occlusion Virtual Try-on by Semantically-Guided Mixup (TMM 2023)
anaconda3
pytorch 1.1.0
torchvision 0.3.0
cuda 9.0
cupy 6.0.0
opencv-python 4.5.1
python 3.6
conda create -n tryon python=3.6
source activate tryon or conda activate tryon
conda install pytorch=1.1.0 torchvision=0.3.0 cudatoolkit=9.0 -c pytorch
conda install cupy or pip install cupy==6.0.0
pip install opencv-python
python test_w_enhance.py --name demo --resize_or_crop None --batchSize 1 --gpu_ids=1
The use of this code is RESTRICTED to non-commercial research and educational purposes.
Please cite if our work is useful for your research:
@article{2023occlumix,
title={OccluMix: Towards De-Occlusion Virtual Try-on by Semantically-Guided Mixup},
author={Yang, Zhijing and Chen, Junyang and Shi, Yukai and Li, Hao and Chen, Tianshui and Lin, Liang},
journal={arXiv preprint arXiv:2301.00965},
year={2023}
}
@article{2023occlumix,
author={Yang, Zhijing and Chen, Junyang and Shi, Yukai and Li, Hao and Chen, Tianshui and Lin, Liang},
journal={IEEE Transactions on Multimedia},
title={OccluMix: Towards De-Occlusion Virtual Try-On by Semantically-Guided Mixup},
year={2023},
volume={},
number={},
pages={1-12},
doi={10.1109/TMM.2023.3234399}}