# Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution arXiv: https://arxiv.org/abs/2410.10140 · HTML: https://mlsanity.com/paper/2410.10140/ ## Key facts - Cited by 16 papers in the map (data through 14 Oct 2026). - Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba). - Builds on 18 of its 60 references that are in the map. - First posted on arXiv 14 Oct 2024. ## Placed in - State-space sequence models (S4, Mamba) / [Vision Mamba backbones](https://mlsanity.com/ssm/vision-mamba-backbones/) ## Builds on (most cited first, 18 of 18) - [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021) - [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020) - [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024) - [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024) - [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022) - [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024) - [Residual Non-local Attention Networks for Image Restoration](https://mlsanity.com/paper/1903.10082/) (2019) - [PointMamba: A Simple State Space Model for Point Cloud Analysis](https://mlsanity.com/paper/2402.10739/) (2024) - [Transformer for Single Image Super-Resolution](https://mlsanity.com/paper/2108.11084/) (2021) - [VmambaIR: Visual State Space Model for Image Restoration](https://mlsanity.com/paper/2403.11423/) (2024) - [Accurate Image Restoration with Attention Retractable Transformer](https://mlsanity.com/paper/2210.01427/) (2022) - [On Efficient Transformer-Based Image Pre-training for Low-Level Vision](https://mlsanity.com/paper/2112.10175/) (2021) - [Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary](https://mlsanity.com/paper/2401.08209/) (2024) - [Frequency-Assisted Mamba for Remote Sensing Image Super-Resolution](https://mlsanity.com/paper/2405.04964/) (2024) - [CU-Mamba: Selective State Space Models with Channel Learning for Image Restoration](https://mlsanity.com/paper/2404.11778/) (2024) - [DVMSR: Distillated Vision Mamba for Efficient Super-Resolution](https://mlsanity.com/paper/2405.03008/) (2024) - [CFAT: Unleashing TriangularWindows for Image Super-resolution](https://mlsanity.com/paper/2403.16143/) (2024) - [Activating Wider Areas in Image Super-Resolution](https://mlsanity.com/paper/2403.08330/) (2024) ## Built on by (most cited first, 16 of 16) - [MambaIRv2: Attentive State Space Restoration](https://mlsanity.com/paper/2411.15269/) (2024) - [NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results](https://mlsanity.com/paper/2504.14582/) (2025) - [Physics-Driven Autoregressive State Space Models for Medical Image Reconstruction](https://mlsanity.com/paper/2412.09331/) (2024) - [A Survey on Mamba Architecture for Vision Applications](https://mlsanity.com/paper/2502.07161/) (2025) - [Content-Aware Mamba for Learned Image Compression](https://mlsanity.com/paper/2508.02192/) (2025) - [RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought](https://mlsanity.com/paper/2506.16796/) (2025) - [HSRMamba: Contextual Spatial-Spectral State Space Model for Single Image Hyperspectral Super-Resolution](https://mlsanity.com/paper/2501.18500/) (2025) - [MambaLiteSR: Image Super-Resolution with Low-Rank Mamba using Knowledge Distillation](https://mlsanity.com/paper/2502.14090/) (2025) - [FRN: Fractal-Based Recursive Spectral Reconstruction Network](https://mlsanity.com/paper/2505.15439/) (2025) - [PCMamba: Physics-Informed Cross-Modal State Space Model for Dual-Camera Compressive Hyperspectral Imaging](https://mlsanity.com/paper/2505.16373/) (2025) - [Transformer-Progressive Mamba Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2511.03232/) (2025) - [D2-Mamba: Dual-Scale Fusion and Dual-Path Scanning with SSMs for Shadow Removal](https://mlsanity.com/paper/2508.12750/) (2025) - [SP-MoMamba: Superpixel-driven Mixture of State Space Experts for Efficient Image Super-Resolution](https://mlsanity.com/paper/2605.25892/) (2026) - [State Space Models Meet Remote Sensing: A Survey](https://mlsanity.com/paper/2606.25329/) (2026) - [Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes](https://mlsanity.com/paper/2608.10954/) (2026) - [Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity](https://mlsanity.com/paper/2609.25538/) (2026) ## Abstract (arXiv) 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 ×3 SR, compared to the strong lightweight MambaIR.