Zero-shot Adaptation of Stable Diffusion via Plug-in Hierarchical Degradation Representation for Real-World Super-Resolution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918243419029504 |
|---|---|
| author | Liao, Yi-Cheng Weng, Shyang-En Xu, Yu-Syuan Hsiao, Chi-Wei Chiu, Wei-Chen Huang, Ching-Chun |
| author_facet | Liao, Yi-Cheng Weng, Shyang-En Xu, Yu-Syuan Hsiao, Chi-Wei Chiu, Wei-Chen Huang, Ching-Chun |
| contents | Real-World Image Super-Resolution (Real-ISR) aims to recover high-quality images from low-quality inputs degraded by unknown and complex real-world factors. Real-world scenarios involve diverse and coupled degradations, making it necessary to provide diffusion models with richer and more informative guidance. However, existing methods often assume known degradation severity and rely on CLIP text encoders that cannot capture numerical severity, limiting their generalization ability. To address this, we propose \textbf{HD-CLIP} (\textbf{H}ierarchical \textbf{D}egradation CLIP), which decomposes a low-quality image into a semantic embedding and an ordinal degradation embedding that captures ordered relationships and allows interpolation across unseen levels. Furthermore, we integrated it into diffusion models via classifier-free guidance (CFG) and proposed classifier-free projection guidance (CFPG). HD-CLIP leverages semantic cues to guide generative restoration while using degradation cues to suppress undesired hallucinations and artifacts. As a \textbf{plug-and-play module}, HD-CLIP can be seamlessly integrated into various super-resolution frameworks without training, significantly improving detail fidelity and perceptual realism across diverse real-world datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_10340 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Zero-shot Adaptation of Stable Diffusion via Plug-in Hierarchical Degradation Representation for Real-World Super-Resolution Liao, Yi-Cheng Weng, Shyang-En Xu, Yu-Syuan Hsiao, Chi-Wei Chiu, Wei-Chen Huang, Ching-Chun Computer Vision and Pattern Recognition Real-World Image Super-Resolution (Real-ISR) aims to recover high-quality images from low-quality inputs degraded by unknown and complex real-world factors. Real-world scenarios involve diverse and coupled degradations, making it necessary to provide diffusion models with richer and more informative guidance. However, existing methods often assume known degradation severity and rely on CLIP text encoders that cannot capture numerical severity, limiting their generalization ability. To address this, we propose \textbf{HD-CLIP} (\textbf{H}ierarchical \textbf{D}egradation CLIP), which decomposes a low-quality image into a semantic embedding and an ordinal degradation embedding that captures ordered relationships and allows interpolation across unseen levels. Furthermore, we integrated it into diffusion models via classifier-free guidance (CFG) and proposed classifier-free projection guidance (CFPG). HD-CLIP leverages semantic cues to guide generative restoration while using degradation cues to suppress undesired hallucinations and artifacts. As a \textbf{plug-and-play module}, HD-CLIP can be seamlessly integrated into various super-resolution frameworks without training, significantly improving detail fidelity and perceptual realism across diverse real-world datasets. |
| title | Zero-shot Adaptation of Stable Diffusion via Plug-in Hierarchical Degradation Representation for Real-World Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.10340 |