AI 中文总结
该研究针对ANN型AiOIR能耗高、SNN型AiOIR缺乏退化线索的问题，提出SpikeRestormer模型，通过SDEA、HBSM、AREA实现节能AiOIR，性能优于现有SNN方法且能耗显著更低。
AI 中文摘要
基于人工神经网络（ANN）的全合一图像复原（AiOIR）可统一处理多种退化问题，但计算成本高，限制了其实时部署。脉冲神经网络（SNN）是一种低功耗替代方案，然而将其应用于静态图像仍具挑战，原因在于缺乏显式事件信号，且退化线索与场景结构高度纠缠，阻碍了面向可靠复原的脉冲事件学习。为解决这些问题，本文提出SpikeRestormer，一种用于AiOIR的节能SNN，可对内部生成的脉冲线索进行事件推理。具体而言，本文提出退化事件感知过程，通过减法退化事件注意力（SDEA）提取基于脉冲的退化事件；此外，引入分层贝叶斯跳过掩码（HBSM）和加法复原事件注意力（AREA）过程，分别用于事件可靠性推理和复原事件构建。通过整合这些互补过程，SpikeRestormer将复原表述为退化事件感知、退化事件可靠性推理及复原事件构建的统一过程，释放了SNN在节能AiOIR中的潜力。大量实验表明，SpikeRestormer相较于基于ANN的方法表现具有竞争力，且在基于SNN的方法中建立了新的最先进结果，同时能耗显著更低。
英文摘要
ANN-based All-in-One image restoration (AiOIR) unifies diverse degradation handling but incurs high computational costs, limiting its real-time deployment. While Spiking Neural Networks (SNNs) offer a low-power alternative, applying them to static images remains challenging. This difficulty arises because explicit event signals are absent, and degradation cues are heavily entangled with scene structures, hindering the learning of reliable restoration-oriented spike events. To address these issues, we propose SpikeRestormer, an energy-efficient SNN for AiOIR that performs event reasoning over internally generated spike cues. Specifically, we propose a degradation-event perception process to extract spike-based degradation events through Subtractive Degradation Event Attention (SDEA). Moreover, we introduce Hierarchical Bayesian Skip Masking (HBSM) and Additive Restoration Event Attention (AREA) processes for event-reliability inference and restoration-event construction, respectively. By integrating these complementary processes, SpikeRestormer formulates restoration as a unified process of degradation-event perception, degradation-event reliability inference, and restoration-event construction, liberating the potential of SNNs for energy-efficient AiOIR. Extensive experiments show that SpikeRestormer delivers competitive performance against ANN-based methods and establishes new state-of-the-art results among SNN-based methods with significantly lower energy consumption.
