From Local Windows to Adaptive Candidates via Individualized Exploratory: Rethinking Attention for Image Super-Resolution

TL;DR

This paper introduces the Individualized Exploratory Transformer (IET) with a novel attention mechanism that enables each token to adaptively select content-aware attention candidates, improving efficiency and accuracy in image super-resolution.

Contribution

The paper proposes the IET model with a new attention mechanism that allows token-specific adaptive attention, addressing limitations of fixed group-wise attention in super-resolution tasks.

Findings

IET achieves state-of-the-art performance on standard SR benchmarks.

IET maintains high efficiency with lower computational costs.

The individualized attention mechanism improves information aggregation accuracy.

Abstract

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.