Restora-Flow: Mask-Guided Image Restoration with Flow Matching
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908676974968832 |
|---|---|
| author | Hadzic, Arnela Thaler, Franz Bogensperger, Lea Joham, Simon Johannes Urschler, Martin |
| author_facet | Hadzic, Arnela Thaler, Franz Bogensperger, Lea Joham, Simon Johannes Urschler, Martin |
| contents | Flow matching has emerged as a promising generative approach that addresses the lengthy sampling times associated with state-of-the-art diffusion models and enables a more flexible trajectory design, while maintaining high-quality image generation. This capability makes it suitable as a generative prior for image restoration tasks. Although current methods leveraging flow models have shown promising results in restoration, some still suffer from long processing times or produce over-smoothed results. To address these challenges, we introduce Restora-Flow, a training-free method that guides flow matching sampling by a degradation mask and incorporates a trajectory correction mechanism to enforce consistency with degraded inputs. We evaluate our approach on both natural and medical datasets across several image restoration tasks involving a mask-based degradation, i.e., inpainting, super-resolution and denoising. We show superior perceptual quality and processing time compared to diffusion and flow matching-based reference methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_20152 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Restora-Flow: Mask-Guided Image Restoration with Flow Matching Hadzic, Arnela Thaler, Franz Bogensperger, Lea Joham, Simon Johannes Urschler, Martin Computer Vision and Pattern Recognition Flow matching has emerged as a promising generative approach that addresses the lengthy sampling times associated with state-of-the-art diffusion models and enables a more flexible trajectory design, while maintaining high-quality image generation. This capability makes it suitable as a generative prior for image restoration tasks. Although current methods leveraging flow models have shown promising results in restoration, some still suffer from long processing times or produce over-smoothed results. To address these challenges, we introduce Restora-Flow, a training-free method that guides flow matching sampling by a degradation mask and incorporates a trajectory correction mechanism to enforce consistency with degraded inputs. We evaluate our approach on both natural and medical datasets across several image restoration tasks involving a mask-based degradation, i.e., inpainting, super-resolution and denoising. We show superior perceptual quality and processing time compared to diffusion and flow matching-based reference methods. |
| title | Restora-Flow: Mask-Guided Image Restoration with Flow Matching |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.20152 |