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

• URL: http://arxiv.org/abs/2506.07814v1
• Date: Mon, 09 Jun 2025 14:43:39 GMT
• Title: M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration
• Authors: Yongzhen Wang, Yongjun Li, Zhuoran Zheng, Xiao-Ping Zhang, Mingqiang Wei,
• Abstract summary: M2Restore is a novel Mixture-of-Experts (MoE)-based Mamba-CNN fusion framework for efficient and robust all-in-one image restoration.<n>We exploit a CLIP-guided MoE gating mechanism that fuses task-conditioned prompts with CLIP-derived semantic priors.<n>We design a dual-stream architecture that integrates the localized representational strength of CNNs with the long-range modeling efficiency of Mamba.
• Score: 24.997494864875883
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• RD-UIE: Relation-Driven State Space Modeling for Underwater Image Enhancement [59.364418120895]
  Underwater image enhancement (UIE) is a critical preprocessing step for marine vision applications.<n>We develop a novel relation-driven Mamba framework for effective UIE (RD-UIE)<n>Experiments on underwater enhancement benchmarks demonstrate RD-UIE outperforms the state-of-the-art approach WMamba.
  arXiv  Detail & Related papers  (2025-05-02T12:21:44Z)
• Any Image Restoration via Efficient Spatial-Frequency Degradation Adaptation [158.37640586809187]
  Restoring any degraded image efficiently via just one model has become increasingly significant.<n>Our approach, termed AnyIR, takes a unified path that leverages inherent similarity across various degradations.<n>To fuse the degradation awareness and the contextualized attention, a spatial-frequency parallel fusion strategy is proposed.
  arXiv  Detail & Related papers  (2025-04-19T09:54:46Z)
• An Efficient and Mixed Heterogeneous Model for Image Restoration [71.85124734060665]
  Current mainstream approaches are based on three architectural paradigms: CNNs, Transformers, and Mambas.<n>We propose RestorMixer, an efficient and general-purpose IR model based on mixed-architecture fusion.
  arXiv  Detail & Related papers  (2025-04-15T08:19:12Z)
• Contrast: A Hybrid Architecture of Transformers and State Space Models for Low-Level Vision [3.574664325523221]
  We propose textbfContrast, a hybrid SR model that combines textbfConvolutional, textbfTransformer, and textbfState Space components.<n>By integrating transformer and state space mechanisms, textbfContrast compensates for the shortcomings of each approach, enhancing both global context modeling and pixel-level accuracy.
  arXiv  Detail & Related papers  (2025-01-23T03:34:14Z)
• Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging [40.80197280147993]
  We propose a Mamba-inspired Joint Unfolding Network (MiJUN) to overcome the inherent nonlinear and ill-posed characteristics of HSI reconstruction.<n>We introduce an accelerated unfolding network scheme, which reduces the reliance on initial optimization stages.<n>We refine the scanning strategy with Mamba by integrating the tensor mode-$k$ unfolding into the Mamba network.
  arXiv  Detail & Related papers  (2025-01-02T13:56:23Z)
• Mixed Degradation Image Restoration via Local Dynamic Optimization and Conditional Embedding [67.57487747508179]
  Multiple-in-one image restoration (IR) has made significant progress, aiming to handle all types of single degraded image restoration with a single model. In this paper, we propose a novel multiple-in-one IR model that can effectively restore images with both single and mixed degradations.
  arXiv  Detail & Related papers  (2024-11-25T09:26:34Z)
• Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality [69.76121008898677]
  Fine-grained Selective Calibrated CLIP integrates local hard negative loss and selective calibrated regularization. Our evaluations show that FSC-CLIP not only achieves compositionality on par with state-of-the-art models but also retains strong multi-modal capabilities.
  arXiv  Detail & Related papers  (2024-10-07T17:16:20Z)
• Restore Anything Model via Efficient Degradation Adaptation [129.38475243424563]
  RAM takes a unified path that leverages inherent similarities across various degradations to enable efficient and comprehensive restoration.<n> RAM's SOTA performance confirms RAM's SOTA performance, reducing model complexity by approximately 82% in trainable parameters and 85% in FLOPs.
  arXiv  Detail & Related papers  (2024-07-18T10:26:53Z)
• IRSRMamba: Infrared Image Super-Resolution via Mamba-based Wavelet Transform Feature Modulation Model [7.842507196763463]
  IRSRMamba is a novel framework integrating wavelet transform feature modulation for multi-scale adaptation.<n>IRSRMamba outperforms state-of-the-art methods in PSNR, SSIM, and perceptual quality.<n>This work establishes Mamba-based architectures as a promising direction for high-fidelity IR image enhancement.
  arXiv  Detail & Related papers  (2024-05-16T07:49:24Z)
• Modality-Collaborative Transformer with Hybrid Feature Reconstruction for Robust Emotion Recognition [35.15390769958969]
  We propose a unified framework, Modality-Collaborative Transformer with Hybrid Feature Reconstruction (MCT-HFR) MCT-HFR consists of a novel attention-based encoder which concurrently extracts and dynamically balances the intra- and inter-modality relations. During model training, LFI leverages complete features as supervisory signals to recover local missing features, while GFA is designed to reduce the global semantic gap between pairwise complete and incomplete representations.
  arXiv  Detail & Related papers  (2023-12-26T01:59:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.