Incorporating Uncertainty-Guided and Top-k Codebook Matching for Real-World Blind Image Super-Resolution
Incorporating Uncertainty-Guided and Top-k Codebook Matching for Real-World Blind Image Super-Resolution
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.
Weilei Wen、Tianyi Zhang、Qianqian Zhao、Zhaohui Zheng、Chunle Guo、Xiuli Shao、Chongyi Li
计算技术、计算机技术
Weilei Wen,Tianyi Zhang,Qianqian Zhao,Zhaohui Zheng,Chunle Guo,Xiuli Shao,Chongyi Li.Incorporating Uncertainty-Guided and Top-k Codebook Matching for Real-World Blind Image Super-Resolution[EB/OL].(2025-06-09)[2025-07-21].https://arxiv.org/abs/2506.07809.点此复制
评论