Diffusion-based image inpainting with internal learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916278047866880 |
|---|---|
| author | Cherel, Nicolas Almansa, Andrés Gousseau, Yann Newson, Alasdair |
| author_facet | Cherel, Nicolas Almansa, Andrés Gousseau, Yann Newson, Alasdair |
| contents | Diffusion models are now the undisputed state-of-the-art for image generation and image restoration. However, they require large amounts of computational power for training and inference. In this paper, we propose lightweight diffusion models for image inpainting that can be trained on a single image, or a few images. We show that our approach competes with large state-of-the-art models in specific cases. We also show that training a model on a single image is particularly relevant for image acquisition modality that differ from the RGB images of standard learning databases. We show results in three different contexts: texture images, line drawing images, and materials BRDF, for which we achieve state-of-the-art results in terms of realism, with a computational load that is greatly reduced compared to concurrent methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_04206 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diffusion-based image inpainting with internal learning Cherel, Nicolas Almansa, Andrés Gousseau, Yann Newson, Alasdair Computer Vision and Pattern Recognition Diffusion models are now the undisputed state-of-the-art for image generation and image restoration. However, they require large amounts of computational power for training and inference. In this paper, we propose lightweight diffusion models for image inpainting that can be trained on a single image, or a few images. We show that our approach competes with large state-of-the-art models in specific cases. We also show that training a model on a single image is particularly relevant for image acquisition modality that differ from the RGB images of standard learning databases. We show results in three different contexts: texture images, line drawing images, and materials BRDF, for which we achieve state-of-the-art results in terms of realism, with a computational load that is greatly reduced compared to concurrent methods. |
| title | Diffusion-based image inpainting with internal learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.04206 |