OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xia, Zhongyu, Li, Jishuo, Lin, Zhiwei, Wang, Xinhao, Wang, Yongtao, Yang, Ming-Hsuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908379701575680
author Xia, Zhongyu
Li, Jishuo
Lin, Zhiwei
Wang, Xinhao
Wang, Yongtao
Yang, Ming-Hsuan
author_facet Xia, Zhongyu
Li, Jishuo
Lin, Zhiwei
Wang, Xinhao
Wang, Yongtao
Yang, Ming-Hsuan
contents Open-world perception aims to develop a model adaptable to novel domains and various sensor configurations and can understand uncommon objects and corner cases. However, current research lacks sufficiently comprehensive open-world 3D perception benchmarks and robust generalizable methodologies. This paper introduces OpenAD, the first real open-world autonomous driving benchmark for 3D object detection. OpenAD is built upon a corner case discovery and annotation pipeline that integrates with a multimodal large language model (MLLM). The proposed pipeline annotates corner case objects in a unified format for five autonomous driving perception datasets with 2000 scenarios. In addition, we devise evaluation methodologies and evaluate various open-world and specialized 2D and 3D models. Moreover, we propose a vision-centric 3D open-world object detection baseline and further introduce an ensemble method by fusing general and specialized models to address the issue of lower precision in existing open-world methods for the OpenAD benchmark. We host an online challenge on EvalAI. Data, toolkit codes, and evaluation codes are available at https://github.com/VDIGPKU/OpenAD.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17761
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection
Xia, Zhongyu
Li, Jishuo
Lin, Zhiwei
Wang, Xinhao
Wang, Yongtao
Yang, Ming-Hsuan
Computer Vision and Pattern Recognition
Open-world perception aims to develop a model adaptable to novel domains and various sensor configurations and can understand uncommon objects and corner cases. However, current research lacks sufficiently comprehensive open-world 3D perception benchmarks and robust generalizable methodologies. This paper introduces OpenAD, the first real open-world autonomous driving benchmark for 3D object detection. OpenAD is built upon a corner case discovery and annotation pipeline that integrates with a multimodal large language model (MLLM). The proposed pipeline annotates corner case objects in a unified format for five autonomous driving perception datasets with 2000 scenarios. In addition, we devise evaluation methodologies and evaluate various open-world and specialized 2D and 3D models. Moreover, we propose a vision-centric 3D open-world object detection baseline and further introduce an ensemble method by fusing general and specialized models to address the issue of lower precision in existing open-world methods for the OpenAD benchmark. We host an online challenge on EvalAI. Data, toolkit codes, and evaluation codes are available at https://github.com/VDIGPKU/OpenAD.
title OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.17761