Incorporating Uncertainty-Guided and Top-k Codebook Matching for Real-World Blind Image 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_ | 1866912420517117952 |
|---|---|
| author | Wen, Weilei Zhang, Tianyi Zhao, Qianqian Zheng, Zhaohui Guo, Chunle Shao, Xiuli Li, Chongyi |
| author_facet | Wen, Weilei Zhang, Tianyi Zhao, Qianqian Zheng, Zhaohui Guo, Chunle Shao, Xiuli Li, Chongyi |
| contents | Recent advancements in codebook-based real image super-resolution (SR) have shown promising results in real-world applications. The core idea involves matching high-quality image features from a codebook based on low-resolution (LR) image features. However, existing methods face two major challenges: inaccurate feature matching with the codebook and poor texture detail reconstruction. To address these issues, we propose a novel Uncertainty-Guided and Top-k Codebook Matching SR (UGTSR) framework, which incorporates three key components: (1) an uncertainty learning mechanism that guides the model to focus on texture-rich regions, (2) a Top-k feature matching strategy that enhances feature matching accuracy by fusing multiple candidate features, and (3) an Align-Attention module that enhances the alignment of information between LR and HR features. Experimental results demonstrate significant improvements in texture realism and reconstruction fidelity compared to existing methods. We will release the code upon formal publication. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07809 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Incorporating Uncertainty-Guided and Top-k Codebook Matching for Real-World Blind Image Super-Resolution Wen, Weilei Zhang, Tianyi Zhao, Qianqian Zheng, Zhaohui Guo, Chunle Shao, Xiuli Li, Chongyi Computer Vision and Pattern Recognition Recent advancements in codebook-based real image super-resolution (SR) have shown promising results in real-world applications. The core idea involves matching high-quality image features from a codebook based on low-resolution (LR) image features. However, existing methods face two major challenges: inaccurate feature matching with the codebook and poor texture detail reconstruction. To address these issues, we propose a novel Uncertainty-Guided and Top-k Codebook Matching SR (UGTSR) framework, which incorporates three key components: (1) an uncertainty learning mechanism that guides the model to focus on texture-rich regions, (2) a Top-k feature matching strategy that enhances feature matching accuracy by fusing multiple candidate features, and (3) an Align-Attention module that enhances the alignment of information between LR and HR features. Experimental results demonstrate significant improvements in texture realism and reconstruction fidelity compared to existing methods. We will release the code upon formal publication. |
| title | Incorporating Uncertainty-Guided and Top-k Codebook Matching for Real-World Blind Image Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.07809 |