Pose-Guided-Person-Image-Generation

Tensorflow implementation of NIPS 2017 paper Pose Guided Person Image Generation

Network architecture

Dependencies

python 2.7
tensorflow-gpu (1.4.1)
numpy (1.14.0)
Pillow (5.0.0)
scikit-image (0.13.0)
scipy (1.0.1)
matplotlib (2.0.0)

Resources

Pretrained models: Market-1501, DeepFashion.
Training data in tf-record format: Market-1501, DeepFashion.
Testing data in tf-record format: Market-1501, DeepFashion.
Raw data: Market-1501, DeepFashion
Testing results: Market-1501, DeepFashion

TF-record data preparation steps

You can skip this data preparation procedure if directly using the tf-record data files.

cd datasets
./run_convert_market.sh to download and convert the original images, poses, attributes, segmentations
./run_convert_DF.sh to download and convert the original images, poses

Note: we also provide the convert code for Market-1501 Attribute and Market-1501 Segmentation results from PSPNet. These extra info, are provided for further research. In our experiments, pose mask are obtained from pose key-points (see _getPoseMask function in convert .py files).

Training steps

Download the tf-record training data.
Modify the model_dir in the run_market_train.sh/run_DF_train.sh scripts.
run run_market_train.sh/run_DF_train.sh

Note: we use a triplet instead of pair real/fake for adversarial training to keep training more stable.

Testing steps

Download the pretrained models and tf-record testing data.
Modify the model_dir in the run_market_test.sh/run_DF_test.sh scripts.
run run_market_test.sh/run_DF_test.sh

Other implementations

Pytorch implementation Human-Pose-Transfer

Citation

@inproceedings{ma2017pose,
  title={Pose guided person image generation},
  author={Ma, Liqian and Jia, Xu and Sun, Qianru and Schiele, Bernt and Tuytelaars, Tinne and Van Gool, Luc},
  booktitle={Advances in Neural Information Processing Systems},
  pages={405--415},
  year={2017}
}

ryutaro765/Pose-Guided-Person-Image-Generation