# Crafting Query-Aware Selective Attention for Single Image Super-Resolution

arXiv: https://arxiv.org/abs/2504.06634 · HTML: https://mlsanity.com/paper/2504.06634/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 53 references that are in the map.
- First posted on arXiv 9 Apr 2025.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Focal Self-attention for Local-Global Interactions in Vision Transformers](https://mlsanity.com/paper/2107.00641/) (2021)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [Lightweight Image Super-Resolution with Information Multi-distillation Network](https://mlsanity.com/paper/1909.11856/) (2019)
- [Efficient Long-Range Attention Network for Image Super-resolution](https://mlsanity.com/paper/2203.06697/) (2022)
- [BiFormer: Vision Transformer with Bi-Level Routing Attention](https://mlsanity.com/paper/2303.08810/) (2023)
- [Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2105.15075/) (2021)
- [CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention](https://mlsanity.com/paper/2108.00154/) (2021)
- [QuadTree Attention for Vision Transformers](https://mlsanity.com/paper/2201.02767/) (2022)
- [Residual Feature Distillation Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2009.11551/) (2020)
- [Natural Language Processing: State of The Art, Current Trends and Challenges](https://mlsanity.com/paper/1708.05148/) (2017)
- [LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond](https://mlsanity.com/paper/2105.10422/) (2021)
- [A Deep Journey into Super-resolution: A survey](https://mlsanity.com/paper/1904.07523/) (2019)
- [SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution](https://mlsanity.com/paper/2208.11247/) (2022)
- [Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices](https://mlsanity.com/paper/2105.10288/) (2021)
- [VideoGigaGAN: Towards Detail-rich Video Super-Resolution](https://mlsanity.com/paper/2404.12388/) (2024)
- [MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors](https://mlsanity.com/paper/1908.07985/) (2019)
- [Lightweight Image Super-Resolution with Adaptive Weighted Learning Network](https://mlsanity.com/paper/1904.02358/) (2019)
- [Real-World Super-Resolution of Face-Images from Surveillance Cameras](https://mlsanity.com/paper/2102.03113/) (2021)
- [Generative Adversarial Networks for Image Super-Resolution: A Survey](https://mlsanity.com/paper/2204.13620/) (2022)

## Abstract (arXiv)

Single Image Super-Resolution (SISR) reconstructs high-resolution images from low-resolution inputs, enhancing image details. While Vision Transformer (ViT)-based models improve SISR by capturing long-range dependencies, they suffer from quadratic computational costs or employ selective attention mechanisms that do not explicitly focus on query-relevant regions. Despite these advancements, prior work has overlooked how selective attention mechanisms should be effectively designed for SISR. We propose SSCAN, which dynamically selects the most relevant key-value windows based on query similarity, ensuring focused feature extraction while maintaining efficiency. In contrast to prior approaches that apply attention globally or heuristically, our method introduces a query-aware window selection strategy that better aligns attention computation with important image regions. By incorporating fixed-sized windows, SSCAN reduces memory usage and enforces linear token-to-token complexity, making it scalable for large images. Our experiments demonstrate that SSCAN outperforms existing attention-based SISR methods, achieving up to 0.14 dB PSNR improvement on urban datasets, guaranteeing both computational efficiency and reconstruction quality in SISR.