to be published.
- Python 3.7
- NVIDIA GPU + CUDA cuDNN 10.1
- PyTorch 1.8.1
- Releasing inference codes.
- Releasing pre-trained weights.
- Releasing training codes.
- train the model
to be published.
- test the model
to be published.
We use Places2, CelebA-HQ, and Paris Street-View datasets. Liu et al. provides 12k irregular masks as the testing mask.
to be published.
This code based on LGNet. Please consider to cite their papers.
@ARTICLE{9730792,
author={Quan, Weize and Zhang, Ruisong and Zhang, Yong and Li, Zhifeng and Wang, Jue and Yan, Dong-Ming},
journal={IEEE Transactions on Image Processing},
title={Image Inpainting With Local and Global Refinement},
year={2022},
volume={31},
pages={2405-2420}
}