PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ruan, Ciyu, Guo, Ruishan, Gong, Zihang, Xu, Jingao, Yang, Wenhan, Chen, Xinlei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915427830988800
author Ruan, Ciyu
Guo, Ruishan
Gong, Zihang
Xu, Jingao
Yang, Wenhan
Chen, Xinlei
author_facet Ruan, Ciyu
Guo, Ruishan
Gong, Zihang
Xu, Jingao
Yang, Wenhan
Chen, Xinlei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_05307
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining
Ruan, Ciyu
Guo, Ruishan
Gong, Zihang
Xu, Jingao
Yang, Wenhan
Chen, Xinlei
Computer Vision and Pattern Recognition
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.
title PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.05307