# SwinFuse: A Residual Swin Transformer Fusion Network for Infrared and Visible Images

arXiv: https://arxiv.org/abs/2204.11436 · HTML: https://mlsanity.com/paper/2204.11436/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 49 references that are in the map.
- First posted on arXiv 25 Apr 2022.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [DenseFuse: A Fusion Approach to Infrared and Visible Images](https://mlsanity.com/paper/1804.08361/) (2018)
- [SwinTrack: A Simple and Strong Baseline for Transformer Tracking](https://mlsanity.com/paper/2112.00995/) (2021)
- [RFN-Nest: An end-to-end residual fusion network for infrared and visible images](https://mlsanity.com/paper/2103.04286/) (2021)
- [NestFuse: An Infrared and Visible Image Fusion Architecture based on Nest Connection and Spatial/Channel Attention Models](https://mlsanity.com/paper/2007.00328/) (2020)
- [MDLatLRR: A novel decomposition method for infrared and visible image fusion](https://mlsanity.com/paper/1811.02291/) (2018)
- [TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework using Self-Supervised Multi-Task Learning](https://mlsanity.com/paper/2112.01030/) (2021)

## Built on by (most cited first, 25 of 25)

- [Task-Customized Mixture of Adapters for General Image Fusion](https://mlsanity.com/paper/2403.12494/) (2024)
- [Dif-Fusion: Towards High Color Fidelity in Infrared and Visible Image Fusion with Diffusion Models](https://mlsanity.com/paper/2301.08072/) (2023)
- [Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion](https://mlsanity.com/paper/2302.01392/) (2023)
- [Infrared and Visible Image Fusion: From Data Compatibility to Task Adaption](https://mlsanity.com/paper/2501.10761/) (2025)
- [MaeFuse: Transferring Omni Features with Pretrained Masked Autoencoders for Infrared and Visible Image Fusion via Guided Training](https://mlsanity.com/paper/2404.11016/) (2024)
- [SFDFusion: An Efficient Spatial-Frequency Domain Fusion Network for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2410.22837/) (2024)
- [Test-Time Dynamic Image Fusion](https://mlsanity.com/paper/2411.02840/) (2024)
- [CrossFuse: Learning Infrared and Visible Image Fusion by Cross-Sensor Top-K Vision Alignment and Beyond](https://mlsanity.com/paper/2502.14493/) (2025)
- [DFVO: Learning Darkness-free Visible and Infrared Image Disentanglement and Fusion All at Once](https://mlsanity.com/paper/2505.04526/) (2025)
- [Graph Representation Learning for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2311.00291/) (2023)
- [FuseFormer: A Transformer for Visual and Thermal Image Fusion](https://mlsanity.com/paper/2402.00971/) (2024)
- [Dual-modal Prior Semantic Guided Infrared and Visible Image Fusion for Intelligent Transportation System](https://mlsanity.com/paper/2403.16227/) (2024)
- [DePF: A Novel Fusion Approach based on Decomposition Pooling for Infrared and Visible Images](https://mlsanity.com/paper/2305.17376/) (2023)
- [HSFusion: A high-level vision task-driven infrared and visible image fusion network via semantic and geometric domain transformation](https://mlsanity.com/paper/2407.10047/) (2024)
- [DAF-Net: A Dual-Branch Feature Decomposition Fusion Network with Domain Adaptive for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2409.11642/) (2024)
- [Dynamic Brightness Adaptation for Robust Multi-modal Image Fusion](https://mlsanity.com/paper/2411.04697/) (2024)
- [WIFE-Fusion:Wavelet-aware Intra-inter Frequency Enhancement for Multi-model Image Fusion](https://mlsanity.com/paper/2506.03555/) (2025)
- [DCDB: Dynamic Conditional Dual Diffusion Bridge for Ill-posed Multi-Tasks](https://mlsanity.com/paper/2509.03044/) (2025)
- [Three-Dimensional Medical Image Fusion with Deformable Cross-Attention](https://mlsanity.com/paper/2310.06291/) (2023)
- [Double-Shot 3D Shape Measurement with a Dual-Branch Network for Structured Light Projection Profilometry](https://mlsanity.com/paper/2407.14198/) (2024)
- [TeSG: Textual Semantic Guidance for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2506.16730/) (2025)
- [Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework](https://mlsanity.com/paper/2509.05000/) (2025)
- [Entity-Guided Multi-Task Learning for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2601.01870/) (2026)
- [Reversible Efficient Diffusion for Image Fusion](https://mlsanity.com/paper/2601.20260/) (2026)
- [FMRFusion: Frequency-Aware Multi-View Representation Learning for Heterogeneous Image Fusion](https://mlsanity.com/paper/2606.07985/) (2026)

## Abstract (arXiv)

The existing deep learning fusion methods mainly concentrate on the convolutional neural networks, and few attempts are made with transformer. Meanwhile, the convolutional operation is a content-independent interaction between the image and convolution kernel, which may lose some important contexts and further limit fusion performance. Towards this end, we present a simple and strong fusion baseline for infrared and visible images, namelytextit Residual Swin Transformer Fusion Network, termed as SwinFuse. Our SwinFuse includes three parts: the global feature extraction, fusion layer and feature reconstruction. In particular, we build a fully attentional feature encoding backbone to model the long-range dependency, which is a pure transformer network and has a stronger representation ability compared with the convolutional neural networks. Moreover, we design a novel feature fusion strategy based on L1-norm for sequence matrices, and measure the corresponding activity levels from row and column vector dimensions, which can well retain competitive infrared brightness and distinct visible details. Finally, we testify our SwinFuse with nine state-of-the-art traditional and deep learning methods on three different datasets through subjective observations and objective comparisons, and the experimental results manifest that the proposed SwinFuse obtains surprising fusion performance with strong generalization ability and competitive computational efficiency. The code will be available at https://github.com/Zhishe-Wang/SwinFuse.