paper-with-me

홈 › Papers

Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras

2025-02-26 · CVPR 2025 1 · Hoonhee Cho, Jae-Young Kang, YoungHo Kim, Kuk-Jin Yoon

Detecting 3D objects in point clouds plays a crucial role in autonomous driving systems. Recently, advanced multi-modal methods incorporating camera information have achieved notable performance. For a safe and effective autonomous driving system, algorithms that excel not only in accuracy but also in speed and low latency are essential. However, existing algorithms fail to meet these requirements due to the latency and bandwidth limitations of fixed frame rate sensors, e.g., LiDAR and camera. To address this limitation, we introduce asynchronous event cameras into 3D object detection for the first time. We leverage their high temporal resolution and low bandwidth to enable high-speed 3D object detection. Our method enables detection even during inter-frame intervals when synchronized data is unavailable, by retrieving previous 3D information through the event camera. Furthermore, we introduce the first event-based 3D object detection dataset, DSEC-3DOD, which includes ground-truth 3D bounding boxes at 100 FPS, establishing the first benchmark for event-based 3D detectors. The code and dataset are available at https://github.com/mickeykang16/Ev3DOD.

📄 PDF Abstract BibTeX arXiv:2502.19630

Code (1)

mickeykang16/ev3dod 공식 구현 jax

Tasks

3D Object DetectionAutonomous DrivingObjectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

A Challenge to Build Neuro-Symbolic Video Agents

2025-05-20 · Sahil Shah, Harsh Goel, Sai Shankar Narasimhan, Minkyu Choi 외

Modern video understanding systems excel at tasks such as scene classification, object detection, and short video retrieval. However, as video analysis becomes increasingly central to real-world applications, there is a …

Scene ClassificationVideo RetrievalVideo Understanding

DOTIE -- Detecting Objects through Temporal Isolation of Events using a Spiking Architecture

2022-10-03 · Manish Nagaraj, Chamika Mihiranga Liyanagedera, Kaushik Roy

Vision-based autonomous navigation systems rely on fast and accurate object detection algorithms to avoid obstacles. Algorithms and sensors designed for such systems need to be computationally efficient, due to the limit…

Autonomous NavigationObjectobject-detectionObject Detection

Pushing the boundaries of event subsampling in event-based video classification using CNNs

2024-09-13 · Hesam Araghi, Jan van Gemert, Nergis Tomen

Event cameras offer low-power visual sensing capabilities ideal for edge-device applications. However, their high event rate, driven by high temporal details, can be restrictive in terms of bandwidth and computational re…

Event data classificationSensitivityVideo Classification

Structured Context Learning for Generic Event Boundary Detection

2025-11-29 · Xin Gu, Congcong Li, Xinyao Wang, Dexiang Hong 외 arxiv

Generic Event Boundary Detection (GEBD) aims to identify moments in videos that humans perceive as event boundaries. This paper proposes a novel method for addressing this task, called Structured Context Learning, which …

Generic Event Boundary Detection

Pushing the Limits of Asynchronous Graph-based Object Detection with Event Cameras

2022-11-22 · Daniel Gehrig, Davide Scaramuzza

State-of-the-art machine-learning methods for event cameras treat events as dense representations and process them with conventional deep neural networks. Thus, they fail to maintain the sparsity and asynchronous nature …

Graph Neural Networkobject-detectionObject Detection