# SUNet: Swin Transformer UNet for Image Denoising

arXiv: https://arxiv.org/abs/2202.14009 · HTML: https://mlsanity.com/paper/2202.14009/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 41 references that are in the map.
- First posted on arXiv 28 Feb 2022.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [Video Frame Interpolation via Adaptive Convolution](https://mlsanity.com/paper/1703.07514/) (2017)
- [Fully Dense UNet for 2D Sparse Photoacoustic Tomography Artifact Removal](https://mlsanity.com/paper/1808.10848/) (2018)
- [RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans](https://mlsanity.com/paper/1811.01328/) (2018)

## Built on by (most cited first, 30 of 44)

- [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023)
- [Generative Semantic Communication: Diffusion Models Beyond Bit Recovery](https://mlsanity.com/paper/2306.04321/) (2023)
- [Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection](https://mlsanity.com/paper/2303.05768/) (2023)
- [Real-World Denoising via Diffusion Model](https://mlsanity.com/paper/2305.04457/) (2023)
- [A Comprehensive Study of Object Tracking in Low-Light Environments](https://mlsanity.com/paper/2312.16250/) (2023)
- [A Spatio-temporal Aligned SUNet Model for Low-light Video Enhancement](https://mlsanity.com/paper/2403.02408/) (2024)
- [HyPINO: Multi-Physics Neural Operators via HyperPINNs and the Method of Manufactured Solutions](https://mlsanity.com/paper/2509.05117/) (2025)
- [Learning Multi-scale Spatial-frequency Features for Image Denoising](https://mlsanity.com/paper/2506.16307/) (2025)
- [Residual Swin Transformer Channel Attention Network for Image Demosaicing](https://mlsanity.com/paper/2204.07098/) (2022)
- [Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack](https://mlsanity.com/paper/2306.16050/) (2023)
- [Degradation-Modeled Multipath Diffusion for Tunable Metalens Photography](https://mlsanity.com/paper/2506.22753/) (2025)
- [Extreme Weather Nowcasting via Local Precipitation Pattern Prediction](https://mlsanity.com/paper/2602.05204/) (2026)
- [Bagged Deep Image Prior for Recovering Images in the Presence of Speckle Noise](https://mlsanity.com/paper/2402.15635/) (2024)
- [A Mathematical Explanation of UNet](https://mlsanity.com/paper/2410.04434/) (2024)
- [Multilook Coherent Imaging: Theoretical Guarantees and Algorithms](https://mlsanity.com/paper/2505.23594/) (2025)
- [NeurLZ: An Online Neural Learning-Based Method to Enhance Scientific Lossy Compression](https://mlsanity.com/paper/2409.05785/) (2024)
- [Swap-Net: A Memory-Efficient 2.5D Network for Sparse-View 3D Cone Beam CT Reconstruction](https://mlsanity.com/paper/2410.10836/) (2024)
- [ClassLIE: Structure- and Illumination-Adaptive Classification for Low-Light Image Enhancement](https://mlsanity.com/paper/2312.13265/) (2023)
- [ADA-Net: Attention-Guided Domain Adaptation Network with Contrastive Learning for Standing Dead Tree Segmentation Using Aerial Imagery](https://mlsanity.com/paper/2504.04271/) (2025)
- [Considering Image Information and Self-similarity: A Compositional Denoising Network](https://mlsanity.com/paper/2209.06417/) (2022)
- [A residual dense vision transformer for medical image super-resolution with segmentation-based perceptual loss fine-tuning](https://mlsanity.com/paper/2302.11184/) (2023)
- [PLU-Net: Extraction of multi-scale feature fusion](https://mlsanity.com/paper/2302.11806/) (2023)
- [DEMIST: A deep-learning-based task-specific denoising approach for myocardial perfusion SPECT](https://mlsanity.com/paper/2306.04249/) (2023)
- [Counterfactual Image Generation for adversarially robust and interpretable Classifiers](https://mlsanity.com/paper/2310.00761/) (2023)
- [Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing](https://mlsanity.com/paper/2404.05350/) (2024)
- [Going Beyond U-Net: Assessing Vision Transformers for Semantic Segmentation in Microscopy Image Analysis](https://mlsanity.com/paper/2409.16940/) (2024)
- [Aberration Correcting Vision Transformers for High-Fidelity Metalens Imaging](https://mlsanity.com/paper/2412.04591/) (2024)
- [Moir'e Zero: An Efficient and High-Performance Neural Architecture for Moir'e Removal](https://mlsanity.com/paper/2507.22407/) (2025)
- [CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing](https://mlsanity.com/paper/2512.09806/) (2025)
- [MS-DCANet: A Novel Segmentation Network For Multi-Modality COVID-19 Medical Images](https://mlsanity.com/paper/2210.12361/) (2022)

## Abstract (arXiv)

Image restoration is a challenging ill-posed problem which also has been a long-standing issue. In the past few years, the convolution neural networks (CNNs) almost dominated the computer vision and had achieved considerable success in different levels of vision tasks including image restoration. However, recently the Swin Transformer-based model also shows impressive performance, even surpasses the CNN-based methods to become the state-of-the-art on high-level vision tasks. In this paper, we proposed a restoration model called SUNet which uses the Swin Transformer layer as our basic block and then is applied to UNet architecture for image denoising. The source code and pre-trained models are available at https://github.com/FanChiMao/SUNet.