Bipartite Graph Reasoning GANs for Person Image Generation
Hao Tang12, Song Bai2, Philip H.S. Torr2, Nicu Sebe13.
1University of Trento, Italy, 2University of Oxford, UK, 3Huawei Research Ireland, Ireland.
In BMVC 2020 Oral.
The repository offers the official implementation of our paper in PyTorch.
Also see our ECCV 2020 paper XingGAN for Person Image Generation.
Copyright (C) 2019 University of Trento, Italy.
All rights reserved. Licensed under the CC BY-NC-SA 4.0 (Attribution-NonCommercial-ShareAlike 4.0 International)
The code is released for academic research use only. For commercial use, please contact hao.tang@unitn.it.
Clone this repo.
git clone https://github.com/Ha0Tang/BiGraphGAN
cd BiGraphGAN/
This code requires PyTorch 1.0.0 and python 3.6.9+. Please install the following dependencies:
- pytorch 1.0.0
- torchvision
- numpy
- scipy
- scikit-image
- pillow
- pandas
- tqdm
- dominate
To reproduce the results reported in the paper, you need to run experiments on NVIDIA DGX1 with 4 32GB V100 GPUs for DeepFashion, and 1 32GB V100 GPU for Market-1501.
Please follow SelectionGAN to directly download both Market-1501 and DeepFashion datasets.
cd scripts/
sh download_bigraphgan_model.sh market
cd ..
cd market_1501/
Then,
- Change several parameters in
test_market_pretrained.sh
. - Run
sh test_market_pretrained.sh
for testing.
cd scripts/
sh download_bigraphgan_model.sh deepfashion
cd ..
cd deepfashion/
Then,
- Change several parameters in
test_deepfashion_pretrained.sh
. - Run
sh test_deepfashion_pretrained.sh
for testing.
- Go to the market_1501 folder.
- Change several parameters in
train_market.sh
. - Run
sh train_market.sh
for training. - Change several parameters in
test_market.sh
. - Run
sh test_market.sh
for testing.
- Go to the deepfashion folder.
- Change several parameters in
train_deepfashion.sh
. - Run
sh train_deepfashion.sh
for training. - Change several parameters in
test_deepfashion.sh
. - Run
sh test_deepfashion.sh
for testing.
For your convenience, you can directly download the images produced by the authors for qualitative comparisons in your own papers!!!
cd scripts/
sh download_bigraphgan_result.sh market
cd scripts/
sh download_bigraphgan_result.sh deepfashion
We adopt SSIM, mask-SSIM, IS, mask-IS, and PCKh for evaluation of Market-1501. SSIM, IS, PCKh for DeepFashion. Please refer to Pose-Transfer for more details.
This source code is inspired by both Pose-Transfer, GloRe and SelectionGAN.
XingGAN | GestureGAN | C2GAN | SelectionGAN | Guided-I2I-Translation-Papers
If you use this code for your research, please cite our papers.
BiGraphGAN
@inproceedings{tang2020bipartite,
title={Bipartite Graph Reasoning GANs for Person Image Generation},
author={Tang, Hao and Bai, Song and Torr, Philip HS and Sebe, Nicu},
booktitle={BMVC},
year={2020}
}
XingGAN
@inproceedings{tang2020xinggan,
title={XingGAN for Person Image Generation},
author={Tang, Hao and Bai, Song and Zhang, Li and Torr, Philip HS and Sebe, Nicu},
booktitle={ECCV},
year={2020}
}
GestureGAN
@inproceedings{tang2018gesturegan,
title={GestureGAN for Hand Gesture-to-Gesture Translation in the Wild},
author={Tang, Hao and Wang, Wei and Xu, Dan and Yan, Yan and Sebe, Nicu},
booktitle={ACM MM},
year={2018}
}
C2GAN
@inproceedings{tang2019cycleincycle,
title={Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation},
author={Tang, Hao and Xu, Dan and Liu, Gaowen and Wang, Wei and Sebe, Nicu and Yan, Yan},
booktitle={ACM MM},
year={2019}
}
SelectionGAN
@inproceedings{tang2019multi,
title={Multi-channel attention selection gan with cascaded semantic guidance for cross-view image translation},
author={Tang, Hao and Xu, Dan and Sebe, Nicu and Wang, Yanzhi and Corso, Jason J and Yan, Yan},
booktitle={CVPR},
year={2019}
}
@article{tang2020multi,
title={Multi-channel attention selection gans for guided image-to-image translation},
author={Tang, Hao and Xu, Dan and Yan, Yan and Corso, Jason J and Torr, Philip HS and Sebe, Nicu},
journal={arXiv preprint arXiv:2002.01048},
year={2020}
}
If you have any questions/comments/bug reports, feel free to open a github issue or pull a request or e-mail to the author Hao Tang (hao.tang@unitn.it).