Two-stage Mamba-based diffusion model for image restoration
Authors:
Open Access
- 1 July 2025
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-14
Abstract
Image restoration is fundamental in computer vision to restore high-quality images from degraded ones. Recently, models such as the transformer and diffusion have shown notable success in addressing this challenge. However, transformer-based methods face high computational costs due to quadratic complexity, while diffusion-based methods often struggle with suboptimal results due to inaccurate noise estimation. This study proposes Diff-Mamba, a two-stage adaptive Mamba-based diffusion model for image restoration. Diff-Mamba integrates the linear complexity state space model (SSM, also known as Mamba) into image restoration, expanding its applicability to visual data generation. Diff-Mamba mainly consists of two parts: the diffusion state space model (DSSM) and the diffusion feedforward neural network (DFNN). DSSM combines Mamba’s high efficiency with the representative power of diffusion models, enhancing both inference and training. DFNN regulates the information flow, enabling each depthwise convolutional layer to focus on the details of image, thus learning more effective local structures for image restoration. The study’s findings, verified through extensive experiments, indicate that Diff-Mamba outperforms both diffusion-based and transformer-based methods in image deraining, denoising, and deblurring, demonstrating competitive restoration performance with various commonly used datasets. Code is available at https://github.com/maluan-ml/Diff-Mamba.Keywords
Funding Information
- Science and Technology Program of Huaibei (2023HK037)
- Scientific Research Program of Anhui Provincial Ministry of Education (2024AH051686)
- Anhui Shenhua Meat Products Co., Ltd. Cooperation Project (22100084)
- Entrusted Project by Huaibei Mining Group (2023)
- Natural Science Foundation of Hebei Province (F2022201013)
This publication has 38 references indexed in Scilit:
- A cross Transformer for image denoisingInformation Fusion, 2023
- Simple Baselines for Image Restoration2022
- A Multi-Head Convolutional Neural Network with Multi-Path Attention Improves Image Denoising2022
- Learning Enriched Features for Real Image Restoration and Enhancement2020
- Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms2020
- Multi-Temporal Recurrent Neural Networks for Progressive Non-uniform Single Image Deblurring with Incremental Temporal Training2020
- Deep Joint Rain Detection and Removal from a Single Image2017
- Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring2017
- Benchmarking Denoising Algorithms with Real Photographs2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015