学习自适应动态特征：用于全能图像恢复的多τ液态Mamba
Learning Adaptive Dynamical Features via Multi-$τ$ Liquid-Mamba for All-in-one Image Restoration
AI总结：
提出Multi-τ Liquid-Mamba模块，通过输入条件多时间尺度液态离散化改进选择性状态空间建模，实现自适应动态特征学习，在全能图像恢复中达到最优性能。
摘要：
图像恢复旨在从退化观测中恢复高质量图像。最近的基于Mamba的图像恢复模型在建模长距离依赖方面展现出强大潜力，且具有线性复杂度。然而，现有大多数设计仍依赖于单一状态演化时间尺度，这限制了它们对全能图像恢复中空间异质性和任务依赖退化模式的适应性。本文提出Multi-τ Liquid-Mamba，一种自适应状态空间模块，它将输入条件多时间尺度液态离散化引入选择性状态空间建模。该模块不改变整体选择性扫描流程，而是调制多个动态分支的有效离散化步骤，并根据退化感知门控权重自适应融合它们的响应。这种设计使模型能够捕捉快速变化的局部细节和缓慢演变的全局结构，同时保持Mamba关于序列长度的线性缩放特性。重要的是，Multi-τ Liquid-Mamba在保持原始选择性参数化和硬件高效选择性扫描机制的同时调制有效转移动力学，使其成为可无缝集成到现有基于Mamba架构中的即插即用模块。基于此框架，我们开发了Multi-τ Liquid-Mamba图像恢复网络（MLMIR），用于全能图像恢复。在广泛恢复基准上的大量实验表明，MLMIR在全能图像恢复中持续达到最先进性能，同时在任务对齐恢复设置中保持高度竞争力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
