Exploring the Capability of Text-to-Image Diffusion Models with Structural Edge Guidance for Multi-Spectral Satellite Image Inpainting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917614381432832 |
|---|---|
| author | Czerkawski, Mikolaj Tachtatzis, Christos |
| author_facet | Czerkawski, Mikolaj Tachtatzis, Christos |
| contents | The letter investigates the utility of text-to-image inpainting models for satellite image data. Two technical challenges of injecting structural guiding signals into the generative process as well as translating the inpainted RGB pixels to a wider set of MSI bands are addressed by introducing a novel inpainting framework based on StableDiffusion and ControlNet as well as a novel method for RGB-to-MSI translation. The results on a wider set of data suggest that the inpainting synthesized via StableDiffusion suffers from undesired artifacts and that a simple alternative of self-supervised internal inpainting achieves a higher quality of synthesis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_03008 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Exploring the Capability of Text-to-Image Diffusion Models with Structural Edge Guidance for Multi-Spectral Satellite Image Inpainting Czerkawski, Mikolaj Tachtatzis, Christos Computer Vision and Pattern Recognition The letter investigates the utility of text-to-image inpainting models for satellite image data. Two technical challenges of injecting structural guiding signals into the generative process as well as translating the inpainted RGB pixels to a wider set of MSI bands are addressed by introducing a novel inpainting framework based on StableDiffusion and ControlNet as well as a novel method for RGB-to-MSI translation. The results on a wider set of data suggest that the inpainting synthesized via StableDiffusion suffers from undesired artifacts and that a simple alternative of self-supervised internal inpainting achieves a higher quality of synthesis. |
| title | Exploring the Capability of Text-to-Image Diffusion Models with Structural Edge Guidance for Multi-Spectral Satellite Image Inpainting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.03008 |