English

RainDancer: RGB-Event Video Deraining with Rain-Oriented Spiking Dynamics

Computer Vision and Pattern Recognition 2026-07-15 v1

Abstract

Video deraining aims to recover clean visual content from rainy videos for reliable perception under adverse weather. Existing methods mainly rely on RGB sequences and temporal redundancy, but RGB-only restoration remains ambiguous in dynamic rainy scenes, where rain streaks, textures, boundaries, motion, and occlusions may share similar visual patterns. Event cameras provide complementary motion-sensitive cues with high temporal resolution, but event streams also contain sensor noise and background-triggered responses, so direct RGB-Event fusion may introduce cross-modal interference. To address this issue, we propose RainDancer, a progressive RGB-Event video deraining framework based on a decompose-before-interact paradigm. The core idea is to separate rain and background components within each modality before cross-modal interaction. In the RGB branch, frame features are progressively decomposed into rain and background representations. In the event branch, a rain-oriented spiking neural network module captures sparse and bursty event dynamics associated with rain motion. Component-level fusion is then performed between semantically aligned representations for structure preservation and rain suppression. We further introduce event-domain supervision to regularize sparse event reconstruction, structural consistency, and gradient orientation. Experiments on synthetic and real RGB-Event video deraining datasets demonstrate superior quantitative performance, visual quality, and downstream perception robustness. Code is available at https://github.com/AE86-plus/RainDancer.

Cite

@article{arxiv.2607.13802,
  title  = {RainDancer: RGB-Event Video Deraining with Rain-Oriented Spiking Dynamics},
  author = {Kui Jiang and Runzhe Li and Zhaocheng Yu and Guanglu Sun and Junjun Jiang and Xianming Liu},
  journal= {arXiv preprint arXiv:2607.13802},
  year   = {2026}
}