Shortcuts

注意

您正在阅读 MMEditing 0.x。 MMEditing 0.x 会在 2022 年末开始逐步停止维护,建议您及时升级到 MMEditing 1.0 版本,享受由 OpenMMLab 2.0 带来的更多新特性和更佳的性能表现。阅读 MMEditing 1.0 的发版日志代码文档 以了解更多。

补全模型

AOT-GAN (TVCG’2021)

摘要

结果与模型

Places365-Challenge

算法 掩膜类型 分辨率 训练集容量 测试集 l1 损失 PSNR SSIM 下载
AOT-GAN free-form (50-60%) 512x512 500k Places365-val 7.07 19.01 0.682 模型 | 日志
评估指标 掩膜缺损 论文结果 复现结果
L1 (10^-2) 1 – 10% 0.55 0.54
(lower better) 10 – 20% 1.19 1.47
20 – 30% 2.11 2.79
30 – 40% 3.20 4.38
40 – 50% 4.51 6.28
50 – 60% 7.07 10.16
PSNR 1 – 10% 34.79 inf
(higher better) 10 – 20% 29.49 31.22
20 – 30% 26.03 27.65
30 – 40% 23.58 25.06
40 – 50% 21.65 23.01
50 – 60% 19.01 20.05
SSIM 1 – 10% 0.976 0.982
(higher better) 10 – 20% 0.940 0.951
20 – 30% 0.890 0.911
30 – 40% 0.835 0.866
40 – 50% 0.773 0.815
50 – 60% 0.682 0.739

引用

@inproceedings{yan2021agg,
  author = {Zeng, Yanhong and Fu, Jianlong and Chao, Hongyang and Guo, Baining},
  title = {Aggregated Contextual Transformations for High-Resolution Image Inpainting},
  booktitle = {Arxiv},
  pages={-},
  year = {2020}
}



DeepFillv1 (CVPR’2018)

DeepFillv1 (CVPR'2018)
@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}
}

Places365-Challenge

算法 掩膜类型 分辨率 训练集容量 测试集 l1 损失 PSNR SSIM 下载
DeepFillv1 square bbox 256x256 3500k Places365-val 11.019 23.429 0.862 模型 | 日志

CelebA-HQ

算法 掩膜类型 分辨率 训练集容量 测试集 l1 损失 PSNR SSIM 下载
DeepFillv1 square bbox 256x256 1500k CelebA-val 6.677 26.878 0.911 模型 | 日志



DeepFillv2 (CVPR’2019)

DeepFillv2 (CVPR'2019)
@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}
}

Places365-Challenge

算法 掩膜类型 分辨率 训练集容量 测试集 l1 损失 PSNR SSIM 下载
DeepFillv2 free-form 256x256 100k Places365-val 8.635 22.398 0.815 模型 | 日志

CelebA-HQ

算法 掩膜类型 分辨率 训练集容量 测试集 l1 损失 PSNR SSIM 下载
DeepFillv2 free-form 256x256 20k CelebA-val 5.411 25.721 0.871 模型 | 日志



Global&Local (ToG’2017)

Global&Local (ToG'2017)
@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}
}

请注意,为了与当前的深度图像修复方法进行公平比较,我们没有在 Global&Local 中使用后处理模块。

Places365-Challenge

算法 掩膜类型 分辨率 训练集容量 测试集 l1 损失 PSNR SSIM 下载
Global&Local square bbox 256x256 500k Places365-val 11.164 23.152 0.862 模型 | 日志

CelebA-HQ

算法 掩膜类型 分辨率 训练集容量 测试集 l1 损失 PSNR SSIM 下载
Global&Local square bbox 256x256 500k CelebA-val 6.678 26.780 0.904 模型 | 日志



PConv (ECCV’2018)

PConv (ECCV'2018)
@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}
}

Places365-Challenge

算法 掩膜类型 分辨率 训练集容量 测试集 l1 损失 PSNR SSIM 下载
PConv free-form 256x256 500k Places365-val 8.776 22.762 0.801 模型 | 日志

CelebA-HQ

算法 掩膜类型 分辨率 训练集容量 测试集 l1 损失 PSNR SSIM 下载
PConv free-form 256x256 500k CelebA-val 5.990 25.404 0.853 模型 | 日志



Read the Docs v: master
Versions
master
latest
stable
zyh-doc-notfound-extend
Downloads
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.