This repository includes the implementation for Context-Aware Layout to Image Generation with Enhanced Object Appearance (to appear in CVPR 2021).

This repo is not completely.

• python3
• pytorch >1.0
• numpy
• matplotlib
• opencv

Or install full requirements by running:

pip install -r requirements.txt

• instruction to prepare dataset
• remove all unnecessary files
• add link to download our pre-trained model
• clean code including comments
• instruction for training
• instruction for evaluation
• instruction for applying our methods in layout2img

Download COCO dataset to datasets/coco

bash scripts/download_coco.sh

Download VG dataset to datasets/vg

bash scripts/download_vg.sh
python scripts/preprocess_vg.py

See opts.py for the options. (You can download the pretrained models from here

you can download our trained model from our onedrive repo

You will get the scores close to below after training for around 200 epochs:

If you find this repo helpful, please consider citing:

@inproceedings{he2021context,
  title={Context-Aware Layout to Image Generation with Enhanced Object Appearance},
  author={He, Sen and Liao, Wentong and Yang, Michael and Yang, Yongxin and Song, Yi-Zhe and Rosenhahn, Bodo and Xiang, Tao},
  booktitle={CVPR},
  year={2021}
}

This repository is based on LostGAN, and the propsoed modules can be applied in the layout2img.