BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
Author:
Affiliation:
1. Tsinghua University
2. Centre for Artificial Intelligence and Robotics, HKISI_CAS
3. Sense Time Research
4. Shanghai Artificial Intelligence Laboratory
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/10203037/10203050/10203376.pdf?arnumber=10203376
Reference43 articles.
1. CenterMask: Real-Time Anchor-Free Instance Segmentation
2. Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
3. Joint 3D Proposal Generation and Object Detection from View Aggregation
4. Internimage: Exploring large-scale vision foundation models with deformable convolutions;wang;ArXiv Preprint,2022
5. Bevdepth: Acquisition of reliable depth for multi-view 3d object detection;li;ArXiv Preprint,2022
Cited by 53 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. Sparse agent transformer for unified voxel and image feature extraction and fusion;Information Fusion;2024-10
2. Learning accurate monocular 3D voxel representation via bilateral voxel transformer;Image and Vision Computing;2024-10
3. TS-BEV: BEV object detection algorithm based on temporal-spatial feature fusion;Displays;2024-09
4. Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking With Transformer;IEEE Transactions on Pattern Analysis and Machine Intelligence;2024-09
5. RPEA: A Residual Path Network with Efficient Attention for 3D pedestrian detection from LiDAR point clouds;Expert Systems with Applications;2024-09
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