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

2026-03-16

AI Summary

Existing Transformer-based image restoration methods passively propagate degradation information, struggling to actively suppress such degradation during encoding. This leads to compromised feature learning, high model complexity, and limited generalization. To address this, we propose the M2IR framework, which introduces a Mamba-style state modulation mechanism in the encoding stage to proactively inhibit degradation propagation. In the decoding stage, we design an Adaptive Degradation Expert Collaboration (ADEC) module that integrates a DA-CLIP-guided routing strategy with a shared-expert architecture to precisely remove residual degradation. Our approach pioneers a paradigm shift from passive response to active regulation, achieving state-of-the-art performance across multiple general-purpose image restoration benchmarks while significantly enhancing detail recovery, generalization, and adaptability—and simultaneously reducing model complexity.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Multi-modal Vision
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• image restoration
• degradation propagation
• proactive suppression
• all-in-one restoration
• feature learning

Innovation

• Mamba-style Modulation
• Mixture-of-Experts
• Proactive Image Restoration
• Degradation Suppression
• All-in-One Restoration