提出自适应注意力机制，让图像超分辨率更高效精准
From Local Windows to Adaptive Candidates via Individualized Exploratory: Rethinking Attention for Image Super-Resolution
- 每个像素点自主选择关注对象，打破固定分组限制
- 在相同算力下，峰值信噪比提升0.15~0.32dB，超越现有方法
- 适合追求高精度且受限于计算资源的图像重建场景
单图像超分辨率（SISR）旨在从低分辨率输入重建高分辨率图像。基于Transformer的方法通过建模退化图像中的长程依赖关系取得了显著性能。然而，其特征密集型的注意力计算带来高昂的计算开销。为提升效率，现有方法通常将图像划分为固定分组，并限制每组内的注意力范围。这种分组注意力忽略了标记间固有的相似性不对称性，无法实现灵活的、与标记自适应的注意力计算。为此，我们提出个体探索性Transformer（IET），引入一种新颖的个体探索性注意力（IEA）机制，使每个标记能够自主选择内容感知且独立的注意力候选。这种与标记自适应的非对称设计，在保持计算效率的同时实现了更精确的信息聚合。在标准超分辨率基准上的大量实验表明，IET在相近计算复杂度下达到了最先进的性能。
原文摘要 · Abstract (English)
Single Image Super-Resolution (SISR) is a fundamental computer vision task that aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) input. Transformer-based methods have achieved remarkable performance by modeling long-range dependencies in degraded images. However, their feature-intensive attention computation incurs high computational cost. To improve efficiency, most existing approaches partition images into fixed groups and restrict attention within each group. Such group-wise attention overlooks the inherent asymmetry in token similarities, thereby failing to enable flexible and token-adaptive attention computation. To address this limitation, we propose the Individualized Exploratory Transformer (IET), which introduces a novel Individualized Exploratory Attention (IEA) mechanism that allows each token to adaptively select its own content-aware and independent attention candidates. This token-adaptive and asymmetric design enables more precise information aggregation while maintaining computational efficiency. Extensive experiments on standard SR benchmarks demonstrate that IET achieves state-of-the-art performance under comparable computational complexity.
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。