Saved in:
Bibliographic Details
Main Authors: Liu, Mingjie, Liu, Hanqing, Cui, Luoping, Zhu, Chuang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.02127
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916034114486272
author Liu, Mingjie
Liu, Hanqing
Cui, Luoping
Zhu, Chuang
author_facet Liu, Mingjie
Liu, Hanqing
Cui, Luoping
Zhu, Chuang
contents Object detection in autonomous driving is frequently compromised by complex illumination. While event cameras offer a robust solution, they are susceptible to sudden contrast changes such as reflections which often trigger dense, misleading event signals. To overcome this, we leverage RGB-derived surface normal maps as explicit geometric constraints. Crucially, even when RGB degrades, they preserve low-frequency structural priors that effectively assist in event-based detection. Consequently, we present NRE-Net, a trimodal framework that integrates structural priors from surface Normal maps, appearance context from RGB images, and high-frequency dynamics from Events. The Adaptive Dual-stream Fusion Module (ADFM) first aligns geometric and appearance cues, followed by the Event-modality Aware Fusion Module (EAFM) which selectively integrates event dynamics. Extensive evaluations on DSEC-Det-sub and PKU-DAVIS-SOD demonstrate that incorporating geometric priors yields an additional 3.0% AP50 gain over dual-modal baselines, while our approach consistently outperforms fusion methods such as SFNet (+2.7%) and SODFormer (+7.1%).
format Preprint
id arxiv_https___arxiv_org_abs_2508_02127
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Event-based Object Detection with Monocular Normal Maps
Liu, Mingjie
Liu, Hanqing
Cui, Luoping
Zhu, Chuang
Computer Vision and Pattern Recognition
Object detection in autonomous driving is frequently compromised by complex illumination. While event cameras offer a robust solution, they are susceptible to sudden contrast changes such as reflections which often trigger dense, misleading event signals. To overcome this, we leverage RGB-derived surface normal maps as explicit geometric constraints. Crucially, even when RGB degrades, they preserve low-frequency structural priors that effectively assist in event-based detection. Consequently, we present NRE-Net, a trimodal framework that integrates structural priors from surface Normal maps, appearance context from RGB images, and high-frequency dynamics from Events. The Adaptive Dual-stream Fusion Module (ADFM) first aligns geometric and appearance cues, followed by the Event-modality Aware Fusion Module (EAFM) which selectively integrates event dynamics. Extensive evaluations on DSEC-Det-sub and PKU-DAVIS-SOD demonstrate that incorporating geometric priors yields an additional 3.0% AP50 gain over dual-modal baselines, while our approach consistently outperforms fusion methods such as SFNet (+2.7%) and SODFormer (+7.1%).
title Enhancing Event-based Object Detection with Monocular Normal Maps
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.02127