UniRes: Universal Image Restoration for Complex Degradations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909640837562368 |
|---|---|
| author | Zhou, Mo Ye, Keren Delbracio, Mauricio Milanfar, Peyman Patel, Vishal M. Talebi, Hossein |
| author_facet | Zhou, Mo Ye, Keren Delbracio, Mauricio Milanfar, Peyman Patel, Vishal M. Talebi, Hossein |
| contents | Real-world image restoration is hampered by diverse degradations stemming from varying capture conditions, capture devices and post-processing pipelines. Existing works make improvements through simulating those degradations and leveraging image generative priors, however generalization to in-the-wild data remains an unresolved problem. In this paper, we focus on complex degradations, i.e., arbitrary mixtures of multiple types of known degradations, which is frequently seen in the wild. A simple yet flexible diffusionbased framework, named UniRes, is proposed to address such degradations in an end-to-end manner. It combines several specialized models during the diffusion sampling steps, hence transferring the knowledge from several well-isolated restoration tasks to the restoration of complex in-the-wild degradations. This only requires well-isolated training data for several degradation types. The framework is flexible as extensions can be added through a unified formulation, and the fidelity-quality trade-off can be adjusted through a new paradigm. Our proposed method is evaluated on both complex-degradation and single-degradation image restoration datasets. Extensive qualitative and quantitative experimental results show consistent performance gain especially for images with complex degradations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05599 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UniRes: Universal Image Restoration for Complex Degradations Zhou, Mo Ye, Keren Delbracio, Mauricio Milanfar, Peyman Patel, Vishal M. Talebi, Hossein Computer Vision and Pattern Recognition Real-world image restoration is hampered by diverse degradations stemming from varying capture conditions, capture devices and post-processing pipelines. Existing works make improvements through simulating those degradations and leveraging image generative priors, however generalization to in-the-wild data remains an unresolved problem. In this paper, we focus on complex degradations, i.e., arbitrary mixtures of multiple types of known degradations, which is frequently seen in the wild. A simple yet flexible diffusionbased framework, named UniRes, is proposed to address such degradations in an end-to-end manner. It combines several specialized models during the diffusion sampling steps, hence transferring the knowledge from several well-isolated restoration tasks to the restoration of complex in-the-wild degradations. This only requires well-isolated training data for several degradation types. The framework is flexible as extensions can be added through a unified formulation, and the fidelity-quality trade-off can be adjusted through a new paradigm. Our proposed method is evaluated on both complex-degradation and single-degradation image restoration datasets. Extensive qualitative and quantitative experimental results show consistent performance gain especially for images with complex degradations. |
| title | UniRes: Universal Image Restoration for Complex Degradations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.05599 |