# RouteWinFormer: A Route-Window Transformer for Middle-range Attention in Image Restoration

arXiv: https://arxiv.org/abs/2504.16637 · HTML: https://mlsanity.com/paper/2504.16637/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 23 Apr 2025.

## Builds on (most cited first, 27 of 27)

- [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)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016)
- [Progressive Image Deraining Networks: A Better and Simpler Baseline](https://mlsanity.com/paper/1901.09221/) (2019)
- [Multi-Scale Progressive Fusion Network for Single Image Deraining](https://mlsanity.com/paper/2003.10985/) (2020)
- [Multi-Scale Boosted Dehazing Network with Dense Feature Fusion](https://mlsanity.com/paper/2004.13388/) (2020)
- [DesnowNet: Context-Aware Deep Network for Snow Removal](https://mlsanity.com/paper/1708.04512/) (2017)
- [Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring](https://mlsanity.com/paper/2211.12250/) (2022)
- [Efficient and Explicit Modelling of Image Hierarchies for Image Restoration](https://mlsanity.com/paper/2303.00748/) (2023)
- [Defocus Deblurring Using Dual-Pixel Data](https://mlsanity.com/paper/2005.00305/) (2020)
- [Dense Haze: A benchmark for image dehazing with dense-haze and haze-free images](https://mlsanity.com/paper/1904.02904/) (2019)
- [Single Image Deraining: From Model-Based to Data-Driven and Beyond](https://mlsanity.com/paper/1912.07150/) (2019)
- [Spatially-Adaptive Image Restoration using Distortion-Guided Networks](https://mlsanity.com/paper/2108.08617/) (2021)
- [From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data](https://mlsanity.com/paper/2108.02934/) (2021)
- [Improving Image Restoration by Revisiting Global Information Aggregation](https://mlsanity.com/paper/2112.04491/) (2021)
- [Masked Image Training for Generalizable Deep Image Denoising](https://mlsanity.com/paper/2303.13132/) (2023)
- [MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing](https://mlsanity.com/paper/2207.05621/) (2022)
- [Perceiving and Modeling Density is All You Need for Image Dehazing](https://mlsanity.com/paper/2111.09733/) (2021)
- [Image Restoration for Remote Sensing: Overview and Toolbox](https://mlsanity.com/paper/2107.00557/) (2021)
- [Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration](https://mlsanity.com/paper/2409.19403/) (2024)

## Abstract (arXiv)

Transformer models have recently garnered significant attention in image restoration due to their ability to capture long-range pixel dependencies. However, long-range attention often results in computational overhead without practical necessity, as degradation and context are typically localized. Normalized average attention distance across various degradation datasets shows that middle-range attention is enough for image restoration. Building on this insight, we propose RouteWinFormer, a novel window-based Transformer that models middle-range context for image restoration. RouteWinFormer incorporates Route-Windows Attnetion Module, which dynamically selects relevant nearby windows based on regional similarity for attention aggregation, extending the receptive field to a mid-range size efficiently. In addition, we introduce Multi-Scale Structure Regularization during training, enabling the sub-scale of the U-shaped network to focus on structural information, while the original-scale learns degradation patterns based on generalized image structure priors. Extensive experiments demonstrate that RouteWinFormer outperforms state-of-the-art methods across 9 datasets in various image restoration tasks.