MambaIR: A Simple Baseline for Image Restoration with State-Space Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914972094693376 |
|---|---|
| author | Guo, Hang Li, Jinmin Dai, Tao Ouyang, Zhihao Ren, Xudong Xia, Shu-Tao |
| author_facet | Guo, Hang Li, Jinmin Dai, Tao Ouyang, Zhihao Ren, Xudong Xia, Shu-Tao |
| contents | Recent years have seen significant advancements in image restoration, largely attributed to the development of modern deep neural networks, such as CNNs and Transformers. However, existing restoration backbones often face the dilemma between global receptive fields and efficient computation, hindering their application in practice. Recently, the Selective Structured State Space Model, especially the improved version Mamba, has shown great potential for long-range dependency modeling with linear complexity, which offers a way to resolve the above dilemma. However, the standard Mamba still faces certain challenges in low-level vision such as local pixel forgetting and channel redundancy. In this work, we introduce a simple but effective baseline, named MambaIR, which introduces both local enhancement and channel attention to improve the vanilla Mamba. In this way, our MambaIR takes advantage of the local pixel similarity and reduces the channel redundancy. Extensive experiments demonstrate the superiority of our method, for example, MambaIR outperforms SwinIR by up to 0.45dB on image SR, using similar computational cost but with a global receptive field. Code is available at \url{https://github.com/csguoh/MambaIR}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_15648 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MambaIR: A Simple Baseline for Image Restoration with State-Space Model Guo, Hang Li, Jinmin Dai, Tao Ouyang, Zhihao Ren, Xudong Xia, Shu-Tao Computer Vision and Pattern Recognition Recent years have seen significant advancements in image restoration, largely attributed to the development of modern deep neural networks, such as CNNs and Transformers. However, existing restoration backbones often face the dilemma between global receptive fields and efficient computation, hindering their application in practice. Recently, the Selective Structured State Space Model, especially the improved version Mamba, has shown great potential for long-range dependency modeling with linear complexity, which offers a way to resolve the above dilemma. However, the standard Mamba still faces certain challenges in low-level vision such as local pixel forgetting and channel redundancy. In this work, we introduce a simple but effective baseline, named MambaIR, which introduces both local enhancement and channel attention to improve the vanilla Mamba. In this way, our MambaIR takes advantage of the local pixel similarity and reduces the channel redundancy. Extensive experiments demonstrate the superiority of our method, for example, MambaIR outperforms SwinIR by up to 0.45dB on image SR, using similar computational cost but with a global receptive field. Code is available at \url{https://github.com/csguoh/MambaIR}. |
| title | MambaIR: A Simple Baseline for Image Restoration with State-Space Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.15648 |