Ultralight Polarity-Split Neuromorphic SNN for Event-Stream Super-Resolution
This work addresses fine-grained perception challenges for resource-constrained devices using event cameras, representing an incremental improvement with novel encoding and loss components.
The paper tackles the limited spatial resolution of event cameras by proposing an ultra-lightweight, stream-based event-to-event super-resolution method using Spiking Neural Networks (SNNs), achieving competitive performance on multiple datasets while significantly reducing model size and inference time.
Event cameras offer unparalleled advantages such as high temporal resolution, low latency, and high dynamic range. However, their limited spatial resolution poses challenges for fine-grained perception tasks. In this work, we propose an ultra-lightweight, stream-based event-to-event super-resolution method based on Spiking Neural Networks (SNNs), designed for real-time deployment on resource-constrained devices. To further reduce model size, we introduce a novel Dual-Forward Polarity-Split Event Encoding strategy that decouples positive and negative events into separate forward paths through a shared SNN. Furthermore, we propose a Learnable Spatio-temporal Polarity-aware Loss (LearnSTPLoss) that adaptively balances temporal, spatial, and polarity consistency using learnable uncertainty-based weights. Experimental results demonstrate that our method achieves competitive super-resolution performance on multiple datasets while significantly reducing model size and inference time. The lightweight design enables embedding the module into event cameras or using it as an efficient front-end preprocessing for downstream vision tasks.