用4D状态空间模型实现高速事件相机去雨，兼顾精度与效率
PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining
- 构建4D事件云表征，双时间尺度保留高时序精度
- 在EventRain-27K上达到0.95结构相似性，每秒处理0.4百万事件
- 仅0.26M参数却适配不同雨强、视角及雪天场景
事件相机在高时序分辨率和动态范围方面表现优异，但在雨天会产生密集噪声。现有事件去雨方法在时序精度、去噪效果和计算效率间存在权衡。本文提出PRE-Mamba，一种基于点的事件相机去雨框架，充分挖掘原始事件与雨滴的时空特性。该框架引入4D事件云表示，融合双时间尺度以保持高时序精度；设计时空解耦与融合模块（STDF），通过浅层解耦和交互提升去雨能力；采用多尺度状态空间模型（MS3M），在双时间尺度和多空间尺度下捕捉深层雨滴动态，计算复杂度为线性。结合频域正则化，PRE-Mamba在EventRain-27K数据集上取得0.95结构相似性（SR）、0.91噪声抑制率（NR）和0.4秒/百万事件的处理速度，仅需0.26M参数。此外，方法对不同雨强、视角甚至雪天条件均有良好泛化能力。
原文摘要 · Abstract (English)
Event cameras excel in high temporal resolution and dynamic range but suffer from dense noise in rainy conditions. Existing event deraining methods face trade-offs between temporal precision, deraining effectiveness, and computational efficiency. In this paper, we propose PRE-Mamba, a novel point-based event camera deraining framework that fully exploits the spatiotemporal characteristics of raw event and rain. Our framework introduces a 4D event cloud representation that integrates dual temporal scales to preserve high temporal precision, a Spatio-Temporal Decoupling and Fusion module (STDF) that enhances deraining capability by enabling shallow decoupling and interaction of temporal and spatial information, and a Multi-Scale State Space Model (MS3M) that captures deeper rain dynamics across dual-temporal and multi-spatial scales with linear computational complexity. Enhanced by frequency-domain regularization, PRE-Mamba achieves superior performance (0.95 SR, 0.91 NR, and 0.4s/M events) with only 0.26M parameters on EventRain-27K, a comprehensive dataset with labeled synthetic and real-world sequences. Moreover, our method generalizes well across varying rain intensities, viewpoints, and even snowy conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。