Abstract | ||
---|---|---|
Free-form inpainting is the task of adding new content to an image in the regions specified by an arbitrary binary mask. Most existing approaches train for a certain distribution of masks, which limits their generalization capabilities to unseen mask types. Furthermore, training with pixel-wise and perceptual losses often leads to simple textural extensions towards the missing areas instead of semantically meaningful generation. In this work, we propose RePaint: A Denoising Diffusion Probabilistic Model (DDPM) based inpainting approach that is applicable to even extreme masks. We employ a pretrained unconditional DDPM as the generative prior. To condition the generation process, we only alter the reverse diffusion iterations by sampling the unmasked regions using the given image infor-mation. Since this technique does not modify or condition the original DDPM network itself, the model produces high-quality and diverse output images for any inpainting form. We validate our method for both faces and general-purpose image inpainting using standard and extreme masks. Re-Paint outperforms state-of-the-art Autoregressive, and GAN approaches for at least five out of six mask distributions. Github Repository: git.io/RePaint |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/CVPR52688.2022.01117 | IEEE Conference on Computer Vision and Pattern Recognition |
Keywords | DocType | Volume |
Image and video synthesis and generation | Conference | 2022 |
Issue | Citations | PageRank |
1 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Andreas Lugmayr | 1 | 2 | 1.04 |
Danelljan Martin | 2 | 1344 | 49.35 |
Andres Romero | 3 | 0 | 0.34 |
Fisher Yu | 4 | 1280 | 50.27 |
Radu Timofte | 5 | 1880 | 118.45 |
Luc Van Gool | 6 | 0 | 0.34 |