提升真实图像超分辨率的纹理细节与匹配精度
Incorporating Uncertainty-Guided and Top-k Codebook Matching for Real-World Blind Image Super-Resolution
- 用不确定性引导关注纹理丰富的区域
- 采用Top-k特征匹配融合多候选，提高匹配准确率
- 适合需要高保真纹理重建的图像增强任务
基于码本的现实图像超分辨率近年取得显著进展，核心思想是根据低分辨率（LR）图像特征匹配高质量图像特征。然而现有方法面临两大挑战：码本特征匹配不准、纹理细节重建差。为此，我们提出一种不确定性引导与Top-k码本匹配框架（UGTSR），包含三个关键组件：(1) 不确定性学习机制，引导模型聚焦于纹理丰富的区域；(2) Top-k特征匹配策略，通过融合多个候选特征提升匹配精度；(3) 对齐注意力模块，增强低分辨率与高分辨率特征间的信息对齐。实验表明，该方法在纹理真实性和重建保真度上显著优于现有方法。代码将在正式发表后公开。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。