用可学习的分离核直接增强图像高频细节，提升超分辨率效果。
Enhancing Frequency for Single Image Super-Resolution with Learnable Separable Kernels
- 设计可学习的分离核（LSKs），通过一维分解直接增强图像高频成分。
- 参数量和计算量降低60%以上，且在高倍率放大时性能更优。
- 模块可即插即用，结果可解释，适合轻量化超分模型设计。
现有单图像超分辨率（SISR）方法常通过引入辅助结构（如特殊损失函数）间接提升低分辨率图像质量。本文提出一种即插即用模块——可学习分离核（Learnable Separable Kernels, LSKs），其为形式上的秩一矩阵，可直接增强图像频率成分。从频域角度分析了LSKs适用于SISR任务的原因。基准模型引入LSKs后，参数量与计算开销均减少超过60%，该效果源于将LSKs分解为可正交合并的一维核。此外，对特征图进行可解释性分析，可视化结果表明LSKs能有效增强图像高频成分。大量实验显示，引入LSKs不仅显著降低模型复杂度，还提升了整体性能；尤其在高放大倍数下表现更优。
原文摘要 · Abstract (English)
Existing approaches often enhance the performance of single-image super-resolution (SISR) methods by incorporating auxiliary structures, such as specialized loss functions, to indirectly boost the quality of low-resolution images. In this paper, we propose a plug-and-play module called Learnable Separable Kernels (LSKs), which are formally rank-one matrices designed to directly enhance image frequency components. We begin by explaining why LSKs are particularly suitable for SISR tasks from a frequency perspective. Baseline methods incorporating LSKs demonstrate a significant reduction of over 60\% in both the number of parameters and computational requirements. This reduction is achieved through the decomposition of LSKs into orthogonal and mergeable one-dimensional kernels. Additionally, we perform an interpretable analysis of the feature maps generated by LSKs. Visualization results reveal the capability of LSKs to enhance image frequency components effectively. Extensive experiments show that incorporating LSKs not only reduces the number of parameters and computational load but also improves overall model performance. Moreover, these experiments demonstrate that models utilizing LSKs exhibit superior performance, particularly as the upscaling factor increases.
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。