paper-with-me

홈 › Papers

Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution

2024-10-14 · Junbo Qiao, Jincheng Liao, Wei Li, Yulun Zhang, Yong Guo, Yi Wen, Zhangxizi Qiu, Jiao Xie, Jie Hu, Shaohui Lin

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.

📄 PDF Abstract BibTeX arXiv:2410.10140

Code (0)

등록된 구현이 없습니다.

Tasks

Image Super-ResolutionMambaState Space ModelsSuper-Resolution

Methods 이 논문이 사용한 방법론

Mamba Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.…

Similar Papers 제목 키워드 기반

MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMs

2024-08-21 · Yulin Ren, Xin Li, Mengxi Guo, Bingchen Li 외

We present MambaCSR, a simple but effective framework based on Mamba for the challenging compressed image super-resolution (CSR) task. Particularly, the scanning strategies of Mamba are crucial for effective contextual k…

Compressed Image Super-resolutionImage Super-ResolutionMambaSuper-Resolution

Global and Local Mamba Network for Multi-Modality Medical Image Super-Resolution

2025-04-14 · Zexin Ji, Beiji Zou, Xiaoyan Kui, Sebastien Thureau 외

Convolutional neural networks and Transformer have made significant progresses in multi-modality medical image super-resolution. However, these methods either have a fixed receptive field for local learning or significan…

Image Super-ResolutionMambaState Space ModelsSuper-Resolution

PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition

2024-03-26 · Chenhongyi Yang, Zehui Chen, Miguel Espinosa, Linus Ericsson 외

We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for general visual recognition. The recent Mamba model has shown how SSMs can be highly competitive with other architectures on sequential…

Image ClassificationInstance SegmentationMambaobject-detection+2

HSRMamba: Efficient Wavelet Stripe State Space Model for Hyperspectral Image Super-Resolution

2025-05-16 · Baisong Li, Xingwang Wang, Haixiao Xu

Single hyperspectral image super-resolution (SHSR) aims to restore high-resolution images from low-resolution hyperspectral images. Recently, the Visual Mamba model has achieved an impressive balance between performance …

Computational EfficiencyHyperspectral Image Super-ResolutionImage GenerationImage Super-Resolution+2

VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation

2025-09-04 · Mustafa Munir, Alex Zhang, Radu Marculescu arxiv

Recent advances in Vision Transformers (ViTs) and State Space Models (SSMs) have challenged the dominance of Convolutional Neural Networks (CNNs) in computer vision. ViTs excel at capturing global context, and SSMs like …

Semantic Segmentation