AI 中文总结
针对旧照片多耦合退化问题，本文提出带退化感知与共享记忆的轻量循环状态空间框架Loop-Mamba，引入SGDE与S²M-Mamba，在SynOld基准上优于现有SOTA方法。
AI 中文摘要
旧照片常存在划痕、裂纹、褪色、模糊、噪声及缺失区域等多种耦合退化，严重降低视觉质量与语义内容。本文提出Loop-Mamba，一种基于循环的轻量状态空间框架，将旧照片修复建模为渐进式状态演化，其中持久修复状态通过迭代计算持续传播与优化。具体而言，我们引入语义引导退化估计器（SGDE），通过联合预测局部退化图与全局退化分数，显式建模异构退化，为状态演化提供退化感知引导；进一步开发共享结构记忆Mamba（S²M-Mamba），在迭代间维护持久修复状态，通过共享结构记忆实现持久状态演化，以实现鲁棒的长程结构重建。得益于一阶状态递归，Loop-Mamba通过循环转换传播潜在修复状态，而非重复堆叠深度特征变换，从而缓解梯度稀释，同时避免基于迭代CNN与Transformer的修复框架固有的计算开销；轻量多方向扫描策略进一步增强方向信息聚合，保留结构连续性。为更好评估修复质量，我们引入面向任务的旧照片损伤恢复分数（ODRS），联合衡量退化恢复与结构重建保真度。在公开SynOld基准上的实验表明，Loop-Mamba在常规修复指标及所提ODRS上均持续优于现有最先进方法。
英文摘要
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.
