Learning Adaptive Dynamical Features via Multi-$τ$ Liquid-Mamba for All-in-one Image Restoration

2026-06-21

AI Summary

Existing Mamba-based image restoration models are constrained by a single timescale, limiting their ability to adapt to spatial heterogeneity and task-specific degradation patterns. To address this, this work proposes the Multi-τ Liquid-Mamba (MLM) module, which introduces an input-conditioned, learnable multi-timescale liquid discretization mechanism. This design enables adaptive fusion of dynamic responses from fast-varying local details and slow-varying global structures while preserving linear computational complexity and hardware efficiency. Built upon the MLM module, the resulting MLMIR network achieves state-of-the-art performance across multiple universal image restoration benchmarks and demonstrates strong competitiveness under task-aligned evaluation settings.

Abstract

Image restoration aims to recover high-quality images from degraded observations. Recent Mamba-based image restoration models have demonstrated strong potential in modeling long-range dependencies with linear complexity. However, most existing designs still rely on a single state-evolution timescale, which limits their adaptability to spatially heterogeneous and task-dependent degradation patterns in all-in-one image restoration. In this paper, we propose Multi-$τ$ Liquid-Mamba, an adaptive state space module that introduces input-conditioned multi-timescale liquid discretization into selective state space modeling. Instead of changing the overall selective scan pipeline, the proposed module modulates the effective discretization steps of multiple dynamical branches and adaptively fuses their responses according to degradation-aware gating weights. This design allows the model to capture both fast-varying local details and slowly evolving global structures while preserving the linear scaling property of Mamba with respect to sequence length. Importantly, Multi-$τ$ Liquid-Mamba modulates the effective transition dynamics while preserving the original selective parameterization and hardware-efficient selective scan mechanism, making it a plug-and-play module that can be seamlessly integrated into existing Mamba-based architectures. Built upon this framework, we develop a Multi-$τ$ Liquid-Mamba Image Restoration Network (MLMIR) for all-in-one image restoration. Extensive experiments on a wide range of restoration benchmarks demonstrate that MLMIR consistently achieves state-of-the-art performance in all-in-one image restoration while remaining highly competitive in task-aligned restoration settings.

Problem

• image restoration
• all-in-one restoration
• state space model
• multi-timescale dynamics
• degradation adaptability

Innovation

• Multi-timescale
• Liquid Discretization
• Selective State Space Model
• Adaptive Gating
• All-in-one Image Restoration