SpikeRestormer: Towards Energy-Efficient All-in-One Image Restoration via Unified Event Reasoning
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created SpikeRestormer, a special kind of neural network called a Spiking Neural Network (SNN), to fix different kinds of image problems more efficiently. Unlike usual methods that use a lot of power, their approach uses low energy by generating and using internal spike signals related to image damage. They built parts that help the network recognize and trust these spikes to improve image restoration. Their tests showed that SpikeRestormer works as well as regular methods but uses much less energy.
Spiking Neural Networks (SNNs)Artificial Neural Networks (ANNs)Image RestorationDegradation EventSpike SignalsAttention MechanismEnergy EfficiencyHierarchical BayesianEvent PerceptionAdditive Restoration
Authors
Shengkai Hu, Jie Shao, Jiaqi Ma, Xu Zhang, Keying Wu, Qilu Zhu, Beihang Song, Jun Wan
Abstract
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.