Exploring Recurrent Long-Term Temporal Fusion for Multi-View 3D Perception

Author:

Han Chunrui1ORCID,Yang Jinrong2ORCID,Sun Jianjian1ORCID,Ge Zheng1ORCID,Dong Runpei3ORCID,Zhou Hongyu1ORCID,Mao Weixin4ORCID,Peng Yuang5ORCID,Zhang Xiangyu1ORCID

Affiliation:

1. Megvii Technology, Beijing, China

2. Huazhong University of Science and Technology, Wuhan, China

3. Xi'an Jiaotong University, Beijing, China

4. Waseda University, Fukuoka, Japan

5. Tsinghua University, Ji'an, China

Funder

National Science and Technology Major Project

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Reference62 articles.

1. BEVDepth: Acquisition of Reliable Depth for Multi-View 3D Object Detection

2. BEVDet4D: Exploit temporal cues in multi-camera 3D object detection;Huang,2022

3. PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

4. Time will tell: New outlooks and a baseline for temporal multi-view 3D object detection;Park,2023

5. nuScenes: A Multimodal Dataset for Autonomous Driving

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Focus on your Geometry: Exploiting the Potential of Multi-Frame Stereo Depth Estimation Pre-training for 3D Object Detection;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

2. Learning Temporal Cues by Predicting Objects Move for Multi-camera 3D Object Detection;2024 IEEE International Conference on Robotics and Automation (ICRA);2024-05-13

3. OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detection;2024 International Conference on 3D Vision (3DV);2024-03-18

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3