# Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration

arXiv: https://arxiv.org/abs/2503.21970 · HTML: https://mlsanity.com/paper/2503.21970/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Mamba for image restoration, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 31 of its 47 references that are in the map.
- First posted on arXiv 27 Mar 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Mamba for image restoration](https://mlsanity.com/ssm/mamba-for-image-restoration/)

## Builds on (most cited first, 30 of 31)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- [Deeply-Recursive Convolutional Network for Image Super-Resolution](https://mlsanity.com/paper/1511.04491/) (2015)
- [LSQ+: Improving low-bit quantization through learnable offsets and better initialization](https://mlsanity.com/paper/2004.09576/) (2020)
- [Densely Connected Pyramid Dehazing Network](https://mlsanity.com/paper/1803.08396/) (2018)
- [Efficient and Explicit Modelling of Image Hierarchies for Image Restoration](https://mlsanity.com/paper/2303.00748/) (2023)
- [MambaIRv2: Attentive State Space Restoration](https://mlsanity.com/paper/2411.15269/) (2024)
- [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)
- [Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation](https://mlsanity.com/paper/2111.14826/) (2021)
- [Towards Accurate Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2303.14341/) (2023)
- [Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary](https://mlsanity.com/paper/2401.08209/) (2024)
- [A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends](https://mlsanity.com/paper/2410.15067/) (2024)
- [PAMS: Quantized Super-Resolution via Parameterized Max Scale](https://mlsanity.com/paper/2011.04212/) (2020)
- [MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration](https://mlsanity.com/paper/2412.20066/) (2024)
- [Shift-tolerant Perceptual Similarity Metric](https://mlsanity.com/paper/2207.13686/) (2022)
- [DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks](https://mlsanity.com/paper/2012.11230/) (2020)
- [MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods](https://mlsanity.com/paper/2501.13484/) (2025)
- [Quamba: A Post-Training Quantization Recipe for Selective State Space Models](https://mlsanity.com/paper/2410.13229/) (2024)

## Built on by (most cited first, 5 of 5)

- [PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement](https://mlsanity.com/paper/2505.12266/) (2025)
- [PillarMamba: Learning Local-Global Context for Roadside Point Cloud via Hybrid State Space Model](https://mlsanity.com/paper/2505.05397/) (2025)
- [RoadMamba: A Dual Branch Visual State Space Model for Road Surface Classification](https://mlsanity.com/paper/2508.01210/) (2025)
- [MambaRaw: Selective State Space Modeling for Efficient 4K Raw Image Reconstruction](https://mlsanity.com/paper/2606.24479/) (2026)
- [Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution](https://mlsanity.com/paper/2610.16261/) (2026)

## Abstract (arXiv)

State-Space Models (SSMs) have attracted considerable attention in Image Restoration (IR) due to their ability to scale linearly sequence length while effectively capturing long-distance dependencies. However, deploying SSMs to edge devices is challenging due to the constraints in memory, computing capacity, and power consumption, underscoring the need for efficient compression strategies. While low-bit quantization is an efficient model compression strategy for reducing size and accelerating IR tasks, SSM suffers substantial performance drops at ultra-low bit-widths (2-4 bits), primarily due to outliers that exacerbate quantization error. To address this challenge, we propose Q-MambaIR, an accurate, efficient, and flexible Quantized Mamba for IR tasks. Specifically, we introduce a Statistical Dynamic-balancing Learnable Scalar (DLS) to dynamically adjust the quantization mapping range, thereby mitigating the peak truncation loss caused by extreme values. Furthermore, we design a Range-floating Flexible Allocator (RFA) with an adaptive threshold to flexibly round values. This approach preserves high-frequency details and maintains the SSM's feature extraction capability. Notably, RFA also enables pre-deployment weight quantization, striking a balance between computational efficiency and model accuracy. Extensive experiments on IR tasks demonstrate that Q-MambaIR consistently outperforms existing quantized SSMs, achieving much higher state-of-the-art (SOTA) accuracy results with only a negligible increase in training computation and storage saving.