Loop-Mamba: A Loop Mamba with Degradation-Aware and Shared Memory for Old Photo Restoration

📄 arXiv: 2608.02346v1 📥 PDF

作者: Runci Bai, Yucheng Xin, Pu Wang, Yongcong Wang, Chen Wu, Dianjie Lu, Guijuan Zhang, Pengwen Dai, Guangwei Gao, Siyuan Yao, Zhuoran Zheng

分类: cs.CV

发布日期: 2026-08-03

💡 一句话要点

提出Loop-Mamba以解决老照片修复中的多重退化问题

🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture)

关键词: 老照片修复 退化估计 共享记忆 状态演化 图像处理 深度学习 计算机视觉

📋 核心要点

  1. 老照片修复面临多种退化问题，现有方法难以有效处理这些复杂的退化情况。
  2. Loop-Mamba通过引入语义引导退化估计器和共享结构记忆，提供了一种新的状态演化框架，提升了修复效果。
  3. 在SynOld基准测试中，Loop-Mamba在传统修复指标和新提出的ODRS上均表现出色，超越了现有方法。

📝 摘要（中文）

老照片常常受到划痕、裂缝、褪色、模糊、噪声和缺失区域等多重退化的影响，严重降低了视觉质量和语义内容。我们提出了Loop-Mamba，这是一种轻量级的基于循环的状态空间框架，将老照片修复视为渐进的状态演化。具体而言，我们引入了语义引导退化估计器（SGDE），通过联合预测局部退化图和全局退化评分，显式建模异构退化，为状态演化提供退化感知指导。此外，我们开发了共享结构记忆Mamba（S²M-Mamba），在迭代过程中保持持久的修复状态，从而通过共享结构记忆实现稳健的长距离结构重建。实验结果表明，Loop-Mamba在公共SynOld基准上始终优于以往的最先进方法。

🔬 方法详解

问题定义：本论文旨在解决老照片修复中存在的多重退化问题，现有方法在处理复杂退化时往往效果不佳，导致视觉质量和语义内容的损失。

核心思路：Loop-Mamba的核心思路是将老照片修复视为一种渐进的状态演化过程，通过持续传播和细化修复状态来实现高质量的修复。

技术框架：整体架构包括两个主要模块：语义引导退化估计器（SGDE）用于建模退化，和共享结构记忆Mamba（S²M-Mamba）用于保持持久的修复状态。

关键创新：最重要的创新在于引入了SGDE和S²M-Mamba，使得修复过程能够有效地处理异构退化，并通过共享记忆实现长距离结构重建。

关键设计：在技术细节上，采用了轻量级的多方向扫描策略以增强方向信息聚合，同时引入了任务导向的老照片损伤恢复评分（ODRS）来评估修复质量。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示，Loop-Mamba在SynOld基准测试中显著优于以往的最先进方法，尤其在传统修复指标和ODRS上均取得了显著提升，验证了其在老照片修复中的有效性和可靠性。

🎯 应用场景

该研究在老照片修复领域具有广泛的应用潜力，能够为文化遗产保护、历史档案管理以及个人记忆保存等方面提供有效的技术支持。未来，Loop-Mamba可能会扩展到其他图像修复和增强任务中，推动相关领域的发展。

📄 摘要（原文）

Old photographs often suffer from multiple coupled degradations, including scratches, cracks, fading, blur, noise, and missing regions, severely degrading both visual quality and semantic content. We propose Loop-Mamba, a lightweight loop-based state-space framework that formulates old photo restoration as progressive state evolution, where a persis- tent restoration state is continuously propagated and refined through iterative computation. Specifically, we introduce a Semantic-Guided Degradation Estimator (SGDE) to explicitly model heterogeneous degradations by jointly predicting local degradation maps and global degradation scores, providing degradation-aware guidance for state evolution. We further develop a Shared Structural Memory Mamba (S$^2$M- Mamba), which maintains a persistent restoration state across iterations, enabling persistent state evolution through shared structural memory for robust long-range structural reconstruction. Benefiting from first-order state recursion, Loop-Mamba propagates latent restoration states through recurrent tran- sitions instead of repeatedly stacking deep feature transformations, thereby alleviating gradient dilution while avoiding the computational overhead inherent in iterative CNN- and Transformer-based restoration frameworks. A lightweight multi-directional scanning strategy further enhances direc- tional information aggregation and preserves structural continuity. To better evaluate restoration quality, we introduce the task-oriented Old Photo Damage Recovery Score (ODRS), which jointly measures degradation recovery and structural reconstruction fidelity. Experimental results on the public SynOld benchmark demonstrate that Loop-Mamba consistently outperforms previous state-of-the-art methods across both conventional restoration metrics and the proposed ODRS.