Boosting Diffusion Guidance via Learning Degradation-Aware Models for Blind Super Resolution
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917112799297536 |
|---|---|
| author | Lu, Shao-Hao Wang, Ren Huang, Ching-Chun Chiu, Wei-Chen |
| author_facet | Lu, Shao-Hao Wang, Ren Huang, Ching-Chun Chiu, Wei-Chen |
| contents | Recently, diffusion-based blind super-resolution (SR) methods have shown great ability to generate high-resolution images with abundant high-frequency detail, but the detail is often achieved at the expense of fidelity. Meanwhile, another line of research focusing on rectifying the reverse process of diffusion models (i.e., diffusion guidance), has demonstrated the power to generate high-fidelity results for non-blind SR. However, these methods rely on known degradation kernels, making them difficult to apply to blind SR. To address these issues, we present DADiff in this paper. DADiff incorporates degradation-aware models into the diffusion guidance framework, eliminating the need to know degradation kernels. Additionally, we propose two novel techniques: input perturbation and guidance scalar, to further improve our performance. Extensive experimental results show that our proposed method has superior performance over state-of-the-art methods on blind SR benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_08819 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Boosting Diffusion Guidance via Learning Degradation-Aware Models for Blind Super Resolution Lu, Shao-Hao Wang, Ren Huang, Ching-Chun Chiu, Wei-Chen Image and Video Processing Computer Vision and Pattern Recognition Recently, diffusion-based blind super-resolution (SR) methods have shown great ability to generate high-resolution images with abundant high-frequency detail, but the detail is often achieved at the expense of fidelity. Meanwhile, another line of research focusing on rectifying the reverse process of diffusion models (i.e., diffusion guidance), has demonstrated the power to generate high-fidelity results for non-blind SR. However, these methods rely on known degradation kernels, making them difficult to apply to blind SR. To address these issues, we present DADiff in this paper. DADiff incorporates degradation-aware models into the diffusion guidance framework, eliminating the need to know degradation kernels. Additionally, we propose two novel techniques: input perturbation and guidance scalar, to further improve our performance. Extensive experimental results show that our proposed method has superior performance over state-of-the-art methods on blind SR benchmarks. |
| title | Boosting Diffusion Guidance via Learning Degradation-Aware Models for Blind Super Resolution |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.08819 |