Inpainting Models¶
Generative Image Inpainting with Contextual Attention¶
Introduction¶
[ALGORITHM]
@inproceedings{yu2018generative,
title={Generative image inpainting with contextual attention},
author={Yu, Jiahui and Lin, Zhe and Yang, Jimei and Shen, Xiaohui and Lu, Xin and Huang, Thomas S},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
pages={5505--5514},
year={2018}
}
Results and models¶
Places365-Challenge¶
| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
|---|---|---|---|---|---|---|---|---|
| DeepFillv1 | square bbox | 256x256 | 3500k | Places365-val | 11.019 | 23.429 | 0.862 | model | log |
CelebA-HQ¶
| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
|---|---|---|---|---|---|---|---|---|
| DeepFillv1 | square bbox | 256x256 | 1500k | CelebA-val | 6.677 | 26.878 | 0.911 | model | log |
Free-form Image Inpainting with Gated Convolution¶
Introduction¶
[ALGORITHM]
@inproceedings{yu2019free,
title={Free-form image inpainting with gated convolution},
author={Yu, Jiahui and Lin, Zhe and Yang, Jimei and Shen, Xiaohui and Lu, Xin and Huang, Thomas S},
booktitle={Proceedings of the IEEE International Conference on Computer Vision},
pages={4471--4480},
year={2019}
}
Results and models¶
Places365-Challenge¶
| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
|---|---|---|---|---|---|---|---|---|
| DeepFillv2 | free-form | 256x256 | 100k | Places365-val | 8.635 | 22.398 | 0.815 | model | log |
CelebA-HQ¶
| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
|---|---|---|---|---|---|---|---|---|
| DeepFillv2 | free-form | 256x256 | 20k | CelebA-val | 5.411 | 25.721 | 0.871 | model | log |
Globally and Locally Consistent Image Completion¶
Introduction¶
[ALGORITHM]
@article{iizuka2017globally,
title={Globally and locally consistent image completion},
author={Iizuka, Satoshi and Simo-Serra, Edgar and Ishikawa, Hiroshi},
journal={ACM Transactions on Graphics (ToG)},
volume={36},
number={4},
pages={1--14},
year={2017},
publisher={ACM New York, NY, USA}
}
Note that we do not apply the post-processing module in Global&Local for a fair comparison with current deep inpainting methods.
Results and models¶
Places365-Challenge¶
| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
|---|---|---|---|---|---|---|---|---|
| Global&Local | square bbox | 256x256 | 500k | Places365-val | 11.164 | 23.152 | 0.862 | model | log |
CelebA-HQ¶
| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
|---|---|---|---|---|---|---|---|---|
| Global&Local | square bbox | 256x256 | 500k | CelebA-val | 6.678 | 26.780 | 0.904 | model | log |
Image inpainting for Irregular Holes using Partial Convolutions¶
Introduction¶
[ALGORITHM]
@inproceedings{liu2018image,
title={Image inpainting for irregular holes using partial convolutions},
author={Liu, Guilin and Reda, Fitsum A and Shih, Kevin J and Wang, Ting-Chun and Tao, Andrew and Catanzaro, Bryan},
booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
pages={85--100},
year={2018}
}