We proposed a novel approach for high-fidelity image inpainting. Specifically, we use a single predictive network to conduct predictive filtering at the image level and deep feature level, simultaneously. The image-level filtering is to recover details, while the deep feature-level filtering is to complete semantic information, which leads to high-fidelity inpainting results. Our method outperforms state-of-the-art methods on three public datasets.[ArXiv]
- Places2 Data of Places365-Standard
- CelebA
- [Dunhuang]
- Mask
- For data folder path (CelebA) organize them as following:
--CelebA
--train
--1-1.png
--valid
--1-1.png
--test
--1-1.png
--mask-train
--1-1.png
--mask-valid
--1-1.png
--mask-test
--0%-20%
--1-1.png
--20%-40%
--1-1.png
--40%-60%
--1-1.png
- Run the code
./data/data_list.py
to generate the data list
python train.py
For the parameters: checkpoints/config.yml, kpn/config.py
python test.py
For the parameters: checkpoints/config.yml, kpn/config.py
- Comparsion with SOTA, see paper for details.
More details are coming soon
Parts of this code were derived from:
https://github.com/tsingqguo/efficientderain
https://github.com/knazeri/edge-connect