Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913544710127616 |
|---|---|
| author | Qiao, Junbo Liao, Jincheng Li, Wei Zhang, Yulun Guo, Yong Wen, Yi Qiu, Zhangxizi Xie, Jiao Hu, Jie Lin, Shaohui |
| author_facet | Qiao, Junbo Liao, Jincheng Li, Wei Zhang, Yulun Guo, Yong Wen, Yi Qiu, Zhangxizi Xie, Jiao Hu, Jie Lin, Shaohui |
| contents | State Space Models (SSM), such as Mamba, have shown strong representation ability in modeling long-range dependency with linear complexity, achieving successful applications from high-level to low-level vision tasks. However, SSM's sequential nature necessitates multiple scans in different directions to compensate for the loss of spatial dependency when unfolding the image into a 1D sequence. This multi-direction scanning strategy significantly increases the computation overhead and is unbearable for high-resolution image processing. To address this problem, we propose a novel Hierarchical Mamba network, namely, Hi-Mamba, for image super-resolution (SR). Hi-Mamba consists of two key designs: (1) The Hierarchical Mamba Block (HMB) assembled by a Local SSM (L-SSM) and a Region SSM (R-SSM) both with the single-direction scanning, aggregates multi-scale representations to enhance the context modeling ability. (2) The Direction Alternation Hierarchical Mamba Group (DA-HMG) allocates the isomeric single-direction scanning into cascading HMBs to enrich the spatial relationship modeling. Extensive experiments demonstrate the superiority of Hi-Mamba across five benchmark datasets for efficient SR. For example, Hi-Mamba achieves a significant PSNR improvement of 0.29 dB on Manga109 for $\times3$ SR, compared to the strong lightweight MambaIR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_10140 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution Qiao, Junbo Liao, Jincheng Li, Wei Zhang, Yulun Guo, Yong Wen, Yi Qiu, Zhangxizi Xie, Jiao Hu, Jie Lin, Shaohui Computer Vision and Pattern Recognition State Space Models (SSM), such as Mamba, have shown strong representation ability in modeling long-range dependency with linear complexity, achieving successful applications from high-level to low-level vision tasks. However, SSM's sequential nature necessitates multiple scans in different directions to compensate for the loss of spatial dependency when unfolding the image into a 1D sequence. This multi-direction scanning strategy significantly increases the computation overhead and is unbearable for high-resolution image processing. To address this problem, we propose a novel Hierarchical Mamba network, namely, Hi-Mamba, for image super-resolution (SR). Hi-Mamba consists of two key designs: (1) The Hierarchical Mamba Block (HMB) assembled by a Local SSM (L-SSM) and a Region SSM (R-SSM) both with the single-direction scanning, aggregates multi-scale representations to enhance the context modeling ability. (2) The Direction Alternation Hierarchical Mamba Group (DA-HMG) allocates the isomeric single-direction scanning into cascading HMBs to enrich the spatial relationship modeling. Extensive experiments demonstrate the superiority of Hi-Mamba across five benchmark datasets for efficient SR. For example, Hi-Mamba achieves a significant PSNR improvement of 0.29 dB on Manga109 for $\times3$ SR, compared to the strong lightweight MambaIR. |
| title | Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.10140 |