GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning
GP-VTON aims to transfer an in-shop garment onto a specific person.
We provide the fine-grained parsing result of the model images and in-shop garment images from two existing high-resolution (1024 x 768) virtual try-on benchmarks, namely, VITON-HD and DressCode.
We provide two version of the parsing results. One is with the original resolution (1024 x 768). Another is with the resolution of 512 x 384, on which our experiment are conducted.
VITON-HD
| Resolution | Google Cloud | Baidu Yun |
|---|---|---|
| 1024 x 768 | Available soon | Available soon |
| 512 x 384 | Download | Download |
DressCode
| Resolution | Google Cloud | Baidu Yun |
|---|---|---|
| 1024 x 768 | Download | Download |
| 512 x 384 | Download | Download |
Install required packages:
pip3 install -r requirements.txt
We conduct experiments on the publicly available VITON-HD and DressCode datasets. For convenience, we provide all of the conditions used in our experiments in the following links.
| Resolution | Google Cloud | Baidu Yun |
|---|---|---|
| VITON-HD(512 x 384) | Download | Download |
| DressCode(512 x 384) | Download (coming soon) | Download (coming soon) |
VITON-HD
Please download the pre-trained model from Google Link or Baidu Yun Link, and put the downloaded directory under root directory of this project.
To test the first stage (i.e., the LFGP warping module), run the following command:
python3 -m torch.distributed.launch --nproc_per_node=8 --master_port=4739 test_warping.py \
--name test_partflow_vitonhd_unpaired_1109 \
--PBAFN_warp_checkpoint 'checkpoints/gp-vton_partflow_vitonhd_usepreservemask_lrarms_1027/PBAFN_warp_epoch_121.pth' \
--resize_or_crop None --verbose --tf_log \
--batchSize 2 --num_gpus 8 --label_nc 14 --launcher pytorch \
--dataroot /home/tiger/datazy/CVPR2023/Datasets/VITONHD \
--image_pairs_txt test_pairs_unpaired_1018.txt
To test the second stage (i.e., the try-on generator), run the following command:
python3 -m torch.distributed.launch --nproc_per_node=8 --master_port=4736 test_tryon.py \
--name test_gpvtongen_vitonhd_unpaired_1109 \
--resize_or_crop None --verbose --tf_log --batchSize 12 --num_gpus 8 --label_nc 14 --launcher pytorch \
--PBAFN_gen_checkpoint 'checkpoints/gp-vton_gen_vitonhd_wskin_wgan_lrarms_1029/PBAFN_gen_epoch_201.pth' \
--dataroot /home/tiger/datazy/CVPR2023/Datasets/VITONHD \
--image_pairs_txt test_pairs_unpaired_1018.txt \
--warproot /home/tiger/datazy/CVPR2023/GP-VTON-partflow_final_kaiwu/sample/test_partflow_vitonhd_unpaired_1109
Note that, in the above two commands, parameter --dataroot refers to the root directory of VITON-HD dataset, parameter --image_pairs_txt refers to the test list, which is put under the root directory of VITON-HD dataset, parameter --warproot in the second command refers to the directory of the warped results generated by the first command. Both of the generated results from the two commands are saved under the directory ./sample/exp_name, in which exp_name is defined by the parameter --name in each command.
VITON-HD
To train the first stage (i.e., the LFGP warping module), run the following command:
python3 -m torch.distributed.launch --nproc_per_node=8 --master_port=7129 train_warping.py \
--name gp-vton_partflow_vitonhd_usepreservemask_lrarms_1027 \
--resize_or_crop None --verbose --tf_log \
--batchSize 2 --num_gpus 8 --label_nc 14 --launcher pytorch \
--dataroot /home/tiger/datazy/CVPR2023/Datasets/VITONHD \
--image_pairs_txt train_pairs_1018.txt \
--display_freq 320 --print_freq 160 --save_epoch_freq 10 --write_loss_frep 320 \
--niter_decay 50 --niter 70 --mask_epoch 70 \
--lr 0.00005
To train the second stage (i.e., the try-on generator), we first need to run the following command to generate the warped results for the flat garments in the training set:
python3 -m torch.distributed.launch --nproc_per_node=8 --master_port=4739 test_warping.py \
--name test_gpvton_lrarms_for_training_1029 \
--PBAFN_warp_checkpoint 'checkpoints/gp-vton_partflow_vitonhd_usepreservemask_lrarms_1027/PBAFN_warp_epoch_121.pth' \
--resize_or_crop None --verbose --tf_log \
--batchSize 2 --num_gpus 8 --label_nc 14 --launcher pytorch \
--dataroot /home/tiger/datazy/CVPR2023/Datasets/VITONHD \
--image_pairs_txt train_pairs_1018.txt
The warped results will saved in the directory sample/test_gpvton_lrarms_for_training_1029. Thus run the following command for training:
python3 -m torch.distributed.launch --nproc_per_node=8 --master_port=4736 train_tryon.py \
--name gp-vton_gen_vitonhd_wskin_wgan_lrarms_1029 \
--resize_or_crop None --verbose --tf_log --batchSize 10 --num_gpus 8 --label_nc 14 --launcher pytorch \
--dataroot /home/tiger/datazy/CVPR2023/Datasets/VITONHD \
--image_pairs_txt train_pairs_1018.txt \
--warproot sample/test_gpvton_lrarms_for_training_1029 \
--display_freq 50 --print_freq 25 --save_epoch_freq 10 --write_loss_frep 25 \
--niter_decay 0 --niter 200 \
--lr 0.0005
- Release the ground truth of the garment parsing and human parsing for two public benchmarks (VITON-HD and DressesCode) used in the paper
- Release the the pretrained model and the inference script for VITON-HD dataset.
- Release the the pretrained model and the inference script for DressCode dataset.
- Release the training script for VITON-HD dataset.
- Release the training script for DressCode dataset.
If you find our code or paper helps, please consider citing:
@inproceedings{xie2023gpvton,
title = {GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning},
author = {Zhenyu, Xie and Zaiyu, Huang and Xin, Dong and Fuwei, Zhao and Haoye, Dong and Xijin, Zhang and Feida, Zhu and Xiaodan, Liang},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2023},
}Thanks to PF-AFN, our code is based on it.
The use of this code is RESTRICTED to non-commercial research and educational purposes.