# M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration

arXiv: https://arxiv.org/abs/2506.07814 · HTML: https://mlsanity.com/paper/2506.07814/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 50 of its 77 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)
- 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 50)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [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)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation](https://mlsanity.com/paper/2401.04722/) (2024)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions](https://mlsanity.com/paper/2111.14813/) (2021)
- [Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models](https://mlsanity.com/paper/2207.14626/) (2022)
- [Attentive Generative Adversarial Network for Raindrop Removal from a Single Image](https://mlsanity.com/paper/1711.10098/) (2017)
- [DesnowNet: Context-Aware Deep Network for Snow Removal](https://mlsanity.com/paper/1708.04512/) (2017)
- [Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning](https://mlsanity.com/paper/1904.05050/) (2019)
- [Efficient and Explicit Modelling of Image Hierarchies for Image Restoration](https://mlsanity.com/paper/2303.00748/) (2023)
- [AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation](https://mlsanity.com/paper/2403.14614/) (2024)
- [Controlling Vision-Language Models for Multi-Task Image Restoration](https://mlsanity.com/paper/2310.01018/) (2023)
- [Dense Haze: A benchmark for image dehazing with dense-haze and haze-free images](https://mlsanity.com/paper/1904.02904/) (2019)
- [AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion](https://mlsanity.com/paper/2310.10123/) (2023)
- [MambaIRv2: Attentive State Space Restoration](https://mlsanity.com/paper/2411.15269/) (2024)
- [OneRestore: A Universal Restoration Framework for Composite Degradation](https://mlsanity.com/paper/2407.04621/) (2024)
- [Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priors](https://mlsanity.com/paper/2103.11298/) (2021)
- [Complexity Experts are Task-Discriminative Learners for Any Image Restoration](https://mlsanity.com/paper/2411.18466/) (2024)
- [Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model](https://mlsanity.com/paper/2403.11157/) (2024)
- [GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions](https://mlsanity.com/paper/2305.17863/) (2023)
- [Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining](https://mlsanity.com/paper/2404.01547/) (2024)
- [MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration](https://mlsanity.com/paper/2412.20066/) (2024)

## Built on by (most cited first, 7 of 7)

- [ClusIR: Towards Cluster-Guided All-in-One Image Restoration](https://mlsanity.com/paper/2512.10948/) (2025)
- [FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration](https://mlsanity.com/paper/2511.14099/) (2025)
- [Learning Adaptive Dynamical Features via Multi-τ Liquid-Mamba for All-in-one Image Restoration](https://mlsanity.com/paper/2606.22801/) (2026)
- [CoRE-UIR: Prior-guided common and residual experts for efficient all-in-one remote sensing image restoration](https://mlsanity.com/paper/2607.27898/) (2026)
- [SpikeRestormer: Towards Energy-Efficient All-in-One Image Restoration via Unified Event Reasoning](https://mlsanity.com/paper/2608.02290/) (2026)
- [Degradation-Aware Adaptive Context Gating for Unified Image Restoration](https://mlsanity.com/paper/2605.01236/) (2026)
- [State-Isolated Vision Mamba via Update-Tendency Routing for Underwater Image Enhancement](https://mlsanity.com/paper/2610.13720/) (2026)

## Abstract (arXiv)

Natural images are often degraded by complex, composite degradations such as rain, snow, and haze, which adversely impact downstream vision applications. While existing image restoration efforts have achieved notable success, they are still hindered by two critical challenges: limited generalization across dynamically varying degradation scenarios and a suboptimal balance between preserving local details and modeling global dependencies. To overcome these challenges, we propose M2Restore, a novel Mixture-of-Experts (MoE)-based Mamba-CNN fusion framework for efficient and robust all-in-one image restoration. M2Restore introduces three key contributions: First, to boost the model's generalization across diverse degradation conditions, we exploit a CLIP-guided MoE gating mechanism that fuses task-conditioned prompts with CLIP-derived semantic priors. This mechanism is further refined via cross-modal feature calibration, which enables precise expert selection for various degradation types. Second, to jointly capture global contextual dependencies and fine-grained local details, we design a dual-stream architecture that integrates the localized representational strength of CNNs with the long-range modeling efficiency of Mamba. This integration enables collaborative optimization of global semantic relationships and local structural fidelity, preserving global coherence while enhancing detail restoration. Third, we introduce an edge-aware dynamic gating mechanism that adaptively balances global modeling and local enhancement by reallocating computational attention to degradation-sensitive regions. This targeted focus leads to more efficient and precise restoration. Extensive experiments across multiple image restoration benchmarks validate the superiority of M2Restore in both visual quality and quantitative performance.