Saved in:
Bibliographic Details
Main Authors: Meng, Chunyu, Long, Wei, Gu, Shuhang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.08341
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908761470271488
author Meng, Chunyu
Long, Wei
Gu, Shuhang
author_facet Meng, Chunyu
Long, Wei
Gu, Shuhang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08341
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Local Windows to Adaptive Candidates via Individualized Exploratory: Rethinking Attention for Image Super-Resolution
Meng, Chunyu
Long, Wei
Gu, Shuhang
Computer Vision and Pattern Recognition
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.
title From Local Windows to Adaptive Candidates via Individualized Exploratory: Rethinking Attention for Image Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.08341