M2IR: Proactive All-in-One Image Restoration via Mamba-style Modulation and Mixture-of-Experts

• URL: http://arxiv.org/abs/2603.14816v1
• Date: Mon, 16 Mar 2026 04:37:29 GMT
• Title: M2IR: Proactive All-in-One Image Restoration via Mamba-style Modulation and Mixture-of-Experts
• Abstract summary: M2IR regulates degradation propagation during the encoding stage and efficiently eliminates residual degradations during decoding.<n>Mamba-Style Transformer (MST) block performs pixel-wise selective state modulation to mitigate degradations.<n> Adaptive Degradation Expert Collaboration (ADEC) module utilizes degradation-specific experts guided by a DA-CLIP-driven router and complemented by a shared expert to eliminate residual degradations.
• Score: 38.201178244663765
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Transformer-based architectures have dominated recent advances in all-in-one image restoration, they remain fundamentally reactive: propagating degradations rather than proactively suppressing them. In the absence of explicit suppression mechanisms, degraded signals interfere with feature learning, compelling the decoder to balance artifact removal and detail preservation, thereby increasing model complexity and limiting adaptability. To address these challenges, we propose M2IR, a novel restoration framework that proactively regulates degradation propagation during the encoding stage and efficiently eliminates residual degradations during decoding. Specifically, the Mamba-Style Transformer (MST) block performs pixel-wise selective state modulation to mitigate degradations while preserving structural integrity. In parallel, the Adaptive Degradation Expert Collaboration (ADEC) module utilizes degradation-specific experts guided by a DA-CLIP-driven router and complemented by a shared expert to eliminate residual degradations through targeted and cooperative restoration. By integrating the MST block and ADEC module, M2IR transitions from passive reaction to active degradation control, effectively harnessing learned representations to achieve superior generalization, enhanced adaptability, and refined recovery of fine-grained details across diverse all-in-one image restoration benchmarks. Our source codes are available at https://github.com/Im34v/M2IR.

Related papers

• Degradation-Aware Prompt Learning with Cross-Modal Compensation for Adverse Weather Removal [56.34780145346335]
  Degradation-Aware Cross-Modal Prompt Compensation Network (DCMPC-Net)<n>DCMPC-Net consists of the Cross-Modal Prompt Generator (CMPG), Prompt-Guided Attention Alignment Module (PGAAM), and Dual Feature Compensation Module (DFCM)<n> experiments show that DCMPC-Net outperforms state-of-the-art methods in both task-specific and unified settings.
  arXiv  Detail & Related papers  (2026-08-07T08:13:40Z)
• What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restoration [22.756769058194788]
  We propose DAR-Net, a Dual-Ambiguity Rectification Network for all-in-one image restoration.<n>DAR-Net first introduces a structured degradation state through simplex-constrained archetype mixture modeling.<n>A Semantic Ambiguity Rectification (SeAR) module generates degradation-aware prompts to improve channel-wise conditioning in the decoder.
  arXiv  Detail & Related papers  (2026-07-30T17:01:24Z)
• CURE: Controllable Unified Image Restoration for Complex Degradations [11.660815850318114]
  CURE is a unified framework that enables controllable restoration in complex degradation settings.<n>CURE delivers state-of-the-art performance on composite degradation benchmarks.
  arXiv  Detail & Related papers  (2026-07-03T07:34:11Z)
• Degradation-Aware Adaptive Context Gating for Unified Image Restoration [57.06559692537862]
  Unified image restoration using a single model often faces task interference due to diverse degradations.<n>We propose DACG-IR, which enables explicit perception of degradation characteristics to dynamically modulate feature representations.<n>Experiments show DACG-IR outperforms state-of-the-art methods in single-task, all-in-one, adverse weather removal, and composite degradation settings.
  arXiv  Detail & Related papers  (2026-05-02T04:18:43Z)
• Compositional-Degradation UAV Image Restoration: Conditional Decoupled MoE Network and A Benchmark [27.358052049742764]
  UAV images are critical for applications such as large-area mapping, infrastructure inspection, and emergency response.<n>In real-world flight environments, a single image is often affected by multiple degradation factors, including rain, haze, and noise.<n>We propose DAME-Net, a Degradation-Aware Mixture-of-Experts Network that decouples explicit degradation perception from degradation-conditioned reconstruction.
  arXiv  Detail & Related papers  (2026-04-10T13:27:39Z)
• ClusIR: Towards Cluster-Guided All-in-One Image Restoration [72.16989784735796]
  ClusIR aims to recover high-quality images from diverse degradations within a unified framework.<n>ClusIR comprises two key components: a Probabilistic Cluster-Guided Routing Mechanism (PCGRM) and a Degradation-Aware Frequency Modulation Module (DAFMM)
  arXiv  Detail & Related papers  (2025-12-11T18:59:47Z)
• Learning to Restore Multi-Degraded Images via Ingredient Decoupling and Task-Aware Path Adaptation [51.10017611491389]
  Real-world images often suffer from multiple coexisting degradations, such as rain, noise, and haze coexisting in a single image.<n>We propose an adaptive multi-degradation image restoration network that reconstructs images by leveraging decoupled representations of degradation ingredients.<n>The resulting tightly integrated architecture, termed IMDNet, is extensively validated through experiments.
  arXiv  Detail & Related papers  (2025-11-07T01:50:36Z)
• DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Model [52.44931846016603]
  DPMambaIR is a novel All-in-One image restoration framework that introduces a fine-grained degradation extractor and a Degradation-Aware Prompt State Space Model.<n> experiments show DPMambaIR achieves the best performance, with 27.69dB and 0.893 in PSNR and SSIM, respectively.
  arXiv  Detail & Related papers  (2025-04-24T16:46:32Z)
• Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorers [53.298698981438]
  This paper proposes a new task setting, i.e. Universal Image Restoration (UIR)<n>UIR doesn't require training on all the degradation combinations but only on a set of degradation bases and then removing any degradation that these bases can potentially compose in a zero-shot manner.<n>We propose Chain-of-Restoration (CoR) mechanism, which instructs models to remove unknown composite degradations step-by-step.
  arXiv  Detail & Related papers  (2024-10-11T10:21:42Z)
• Toward Interactive Modulation for Photo-Realistic Image Restoration [16.610981587637102]
  Modulating image restoration level aims to generate a restored image by altering a factor that represents the restoration strength. This paper presents a Controllable Unet Generative Adversarial Network (CUGAN) to generate high-frequency textures in the modulation tasks.
  arXiv  Detail & Related papers  (2021-05-07T07:05:56Z)

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.