# MatIR: A Hybrid Mamba-Transformer Image Restoration Model

arXiv: https://arxiv.org/abs/2501.18401 · HTML: https://mlsanity.com/paper/2501.18401/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Mamba for image restoration, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 10 of its 72 references that are in the map.
- First posted on arXiv 30 Jan 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Mamba for image restoration](https://mlsanity.com/ssm/mamba-for-image-restoration/)

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [An Empirical Study of Mamba-based Language Models](https://mlsanity.com/paper/2406.07887/) (2024)
- [HAT: Hybrid Attention Transformer for Image Restoration](https://mlsanity.com/paper/2309.05239/) (2023)
- [SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolution](https://mlsanity.com/paper/2303.09735/) (2023)
- [CFAT: Unleashing TriangularWindows for Image Super-resolution](https://mlsanity.com/paper/2403.16143/) (2024)
- [When Super-Resolution Meets Camouflaged Object Detection: A Comparison Study](https://mlsanity.com/paper/2308.04370/) (2023)
- [Empowering Image Recovery_ A Multi-Attention Approach](https://mlsanity.com/paper/2404.04617/) (2024)

## Built on by (most cited first, 2 of 2)

- [M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration](https://mlsanity.com/paper/2506.07814/) (2025)
- [VRS-UIE: Value-Driven Reordering Scanning for Underwater Image Enhancement](https://mlsanity.com/paper/2505.01224/) (2025)

## Abstract (arXiv)

In recent years, Transformers-based models have made significant progress in the field of image restoration by leveraging their inherent ability to capture complex contextual features. Recently, Mamba models have made a splash in the field of computer vision due to their ability to handle long-range dependencies and their significant computational efficiency compared to Transformers. However, Mamba currently lags behind Transformers in contextual learning capabilities. To overcome the limitations of these two models, we propose a Mamba-Transformer hybrid image restoration model called MatIR. Specifically, MatIR cross-cycles the blocks of the Transformer layer and the Mamba layer to extract features, thereby taking full advantage of the advantages of the two architectures. In the Mamba module, we introduce the Image Inpainting State Space (IRSS) module, which traverses along four scan paths to achieve efficient processing of long sequence data. In the Transformer module, we combine triangular window-based local attention with channel-based global attention to effectively activate the attention mechanism over a wider range of image pixels. Extensive experimental results and ablation studies demonstrate the effectiveness of our approach.