This is a Pytorch implementation of our paper "Deep Image Blending".

Deep Image Blending
Lingzhi Zhang, Tarmily Wen, Jianbo Shi
GRASP Laboratory, University of Pennsylvania

In Winter Conference on Applications of Computer Vision (WACV), 2020

We propose a Poisson blending loss that achieves the same purpose of Poisson Image Editing. We jointly optimize the proposed Poisson blending loss with style and content loss computed from a deep network, and reconstruct the blending region by iteratively updating the pixels using the L-BFGS solver. In the blending image, we not only smooth out gradient domain of the blending boundary but also add consistent texture into the blending region.

This project uses poetry to manage dependencies; start by install poetry and then dependencies

pip install poetry
poetry install

Once this is done you can run the example. Please check the arguments in the code for you application.

poetry run python run.py
# check arguments
poetry run python run.py --help

If you use this code for your research, please cite our paper:

@inproceedings{zhang2020deep,
  title={Deep Image Blending},
  author={Zhang, Lingzhi and Wen, Tarmily and Shi, Jianbo},
  booktitle={The IEEE Winter Conference on Applications of Computer Vision},
  pages={231--240},
  year={2020}
}