{"ID":2886232,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.03244","arxiv_id":"2508.03244","title":"Ultralight Polarity-Split Neuromorphic SNN for Event-Stream Super-Resolution","abstract":"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.","short_abstract":"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 Spi...","url_abs":"https://arxiv.org/abs/2508.03244","url_pdf":"https://arxiv.org/pdf/2508.03244v2","authors":"[\"Chuanzhi Xu\",\"Haoxian Zhou\",\"Langyi Chen\",\"Yuk Ying Chung\",\"Qiang Qu\"]","published":"2025-08-05T09:24:02Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false}