Two-stage Mamba-based diffusion model for image restoration
Uloženo v:
| Název: | Two-stage Mamba-based diffusion model for image restoration |
|---|---|
| Autoři: | Lei Liu, Luan Ma, Shuai Wang, Jun Wang, Silas N. Melo |
| Zdroj: | Scientific Reports, Vol 15, Iss 1, Pp 1-14 (2025) |
| Informace o vydavateli: | Nature Portfolio, 2025. |
| Rok vydání: | 2025 |
| Sbírka: | LCC:Medicine LCC:Science |
| Témata: | Diffusion Mamba, Image deblurring, Image denoising, Image deraining, Image restoration, Medicine, Science |
| Popis: | 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. |
| Druh dokumentu: | article |
| Popis souboru: | electronic resource |
| Jazyk: | English |
| ISSN: | 2045-2322 |
| Relation: | https://doaj.org/toc/2045-2322 |
| DOI: | 10.1038/s41598-025-07032-3 |
| Přístupová URL adresa: | https://doaj.org/article/a186640e438e49f69687684f1f2194f0 |
| Přístupové číslo: | edsdoj.186640e438e49f69687684f1f2194f0 |
| Databáze: | Directory of Open Access Journals |
Full Text 
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | 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. |
|---|---|
| ISSN: | 20452322 |
| DOI: | 10.1038/s41598-025-07032-3 |