自动驾驶 - arXivDaily 专题

2310.11239 2024-09-11 cs.CV cs.RO 90%

LiDAR-based 4D Occupancy Completion and Forecasting

Xinhao Liu, Moonjun Gong, Qi Fang, Haoyu Xie, Yiming Li, Hang Zhao, Chen Feng

专题命中 BEV与占用：LiDAR(title,abstract)；occupancy(title,abstract)；autonomous driving(abstract)；分类 cs.RO、cs.CV

Comments IROS 2024

2311.16038 2023-11-28 cs.CV cs.AI cs.LG 90%

OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving

Wenzhao Zheng, Weiliang Chen, Yuanhui Huang, Borui Zhang, Yueqi Duan, Jiwen Lu

专题命中 BEV与占用：autonomous driving(title,abstract)；occupancy(title,abstract)；LiDAR(abstract)；分类 cs.CV、cs.AI

Comments Code is available at: https://github.com/wzzheng/OccWorld

2604.02930 2026-04-06 cs.CV 89%

BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving

BEVPredFormer：自动驾驶中用于鸟瞰图实例预测的时空注意力

Miguel Antunes-García, Santiago Montiel-Marín, Fabio Sánchez-García, Rodrigo Gutiérrez-Moreno, Rafael Barea, Luis M. Bergasa

机构 * University of Alcalá（阿尔卡拉大学）

专题命中 BEV与占用：autonomous driving(title,abstract)；BEV(title,abstract)；driving perception(abstract)；分类 cs.CV

AI总结本文提出BEVPredFormer，一种基于相机的新型架构，通过注意力机制提升时空感知能力，解决动态场景中密集空间和时间信息处理的挑战，实验证明其在nuScenes数据集上性能优异。

Comments 15 pages, 5 figures

2603.01007 2026-03-06 cs.CV 89%

Dr.Occ: Depth- and Region-Guided 3D Occupancy from Surround-View Cameras for Autonomous Driving

Dr.Occ: 从环绕视图摄像头获取3D占用的深度和区域引导方法用于自动驾驶

Xubo Zhu, Haoyang Zhang, Fei He, Rui Wu, Yanhu Shan, Wen Yang, Huai Yu

机构 * School of Electronic Information, Wuhan University（武汉大学电子信息学院）； Horizon Robotics ； Wuhan University Shenzhen Research Institute（武汉大学深圳研究院）

专题命中 BEV与占用：autonomous driving(title,abstract)；occupancy(title,abstract)；driving perception(abstract)；分类 cs.CV

AI总结 Dr.Occ通过深度和区域引导方法提升自动驾驶中3D占用预测的几何对齐和语义学习效果。

Comments 10 pages, 6 figures. Accepted at CVPR 2026

2507.23599 2026-03-02 cs.CV 89%

DA-Occ: Direction-Aware 2D Convolution for Efficient and Geometry-Preserving 3D Occupancy Prediction in Autonomous Driving

DA-Occ：方向感知的2D卷积用于自动驾驶中高效且保持几何的3D占用预测

Yuchen Zhou, Yan Luo, Xiaogang Wang, Xingjian Gu, Mingzhou Lu, Xiangbo Shu

专题命中 BEV与占用：autonomous driving(title,abstract)；occupancy(title,abstract)；BEV(abstract)；分类 cs.CV

AI总结 DA-Occ通过方向感知卷积和高度分数投影，在自动驾驶中实现高效且保持几何的3D占用预测，平衡精度与效率。

Comments This manuscript has been withdrawn because we are preparing a significantly revised version with improved methodology and extended experimental evaluation

2504.15888 2025-11-17 cs.CV 89%

MS-Occ: Multi-Stage LiDAR-Camera Fusion for 3D Semantic Occupancy Prediction

Zhiqiang Wei, Lianqing Zheng, Jianan Liu, Tao Huang, Qing-Long Han, Wenwen Zhang, Fengdeng Zhang

机构 * School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology（光学电子与计算机工程学院，上海科学技术大学）； School of Automotive Studies, Tongji University（汽车学院，同济大学）； Momoni AI ； College of Science and Engineering, James Cook University（科学与工程学院，詹姆斯库克大学）； School of Engineering, Swinburne University of Technology（工程学院，斯威本技术大学）； School of Electrical and Electronic Engineering, Nanyang Technological University（电气与电子工程学院，南洋理工大学）

专题命中 BEV与占用：LiDAR(title,abstract)；occupancy(title,abstract)；autonomous driving(abstract)；分类 cs.CV

Comments 8 pages, 5 figures

2507.19370 2025-07-28 cs.CV 89%

BEV-LLM: Leveraging Multimodal BEV Maps for Scene Captioning in Autonomous Driving

Felix Brandstaetter, Erik Schuetz, Katharina Winter, Fabian Flohr

机构 * Intelligent Vehicles Lab (IVL) Munich University of Applied Sciences（智能车辆实验室（IVL）慕尼黑应用科学大学）

专题命中 BEV与占用：autonomous driving(title,abstract)；BEV(title,abstract)；LiDAR(abstract)；分类 cs.CV

2503.18100 2025-03-25 cs.CV 89%

M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving

Xuesong Chen, Shaoshuai Shi, Tao Ma, Jingqiu Zhou, Simon See, Ka Chun Cheung, Hongsheng Li

专题命中 BEV与占用：autonomous driving(title,abstract)；occupancy(title,abstract)；BEV(abstract)；分类 cs.CV

Comments Accepted by AAAI 2025

2408.14197 2025-01-20 cs.CV 89%

Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving

Yu Yang, Jianbiao Mei, Yukai Ma, Siliang Du, Wenqing Chen, Yijie Qian, Yuxiang Feng, Yong Liu

专题命中 BEV与占用：autonomous driving(title,abstract)；occupancy(title,abstract)；BEV(abstract)；分类 cs.CV

Comments Accepted by AAAI2025

2412.20480 2024-12-31 cs.CV 89%

MR-Occ: Efficient Camera-LiDAR 3D Semantic Occupancy Prediction Using Hierarchical Multi-Resolution Voxel Representation

Minjae Seong, Jisong Kim, Geonho Bang, Hawook Jeong, Jun Won Choi

专题命中 BEV与占用：LiDAR(title,abstract)；occupancy(title,abstract)；autonomous driving(abstract)；分类 cs.CV

Comments 11 pages, 5 figures, 9 tables

2409.17659 2024-09-27 cs.AI 89%

Hierarchical End-to-End Autonomous Driving: Integrating BEV Perception with Deep Reinforcement Learning

Siyi Lu, Lei He, Shengbo Eben Li, Yugong Luo, Jianqiang Wang, Keqiang Li

专题命中 BEV与占用：autonomous driving(title,abstract)；BEV(title,abstract)；end-to-end driving(abstract)；分类 cs.AI

2408.11464 2024-08-22 cs.CV 89%

MambaOcc: Visual State Space Model for BEV-based Occupancy Prediction with Local Adaptive Reordering

Yonglin Tian, Songlin Bai, Zhiyao Luo, Yutong Wang, Yisheng Lv, Fei-Yue Wang

专题命中 BEV与占用：BEV(title,abstract)；occupancy(title,abstract)；autonomous driving(abstract)；分类 cs.CV

2312.09243 2024-08-22 cs.CV 89%

OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments

Chubin Zhang, Juncheng Yan, Yi Wei, Jiaxin Li, Li Liu, Yansong Tang, Yueqi Duan, Jiwen Lu

专题命中 BEV与占用：LiDAR(title,abstract)；occupancy(title,abstract)；autonomous driving(abstract)；分类 cs.CV

Comments Code: https://github.com/LinShan-Bin/OccNeRF

2212.05758 2024-01-23 cs.CV 89%

BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios

Zhiwei Lin, Yongtao Wang, Shengxiang Qi, Nan Dong, Ming-Hsuan Yang

专题命中 BEV与占用：autonomous driving(title,abstract)；BEV(title,abstract)；LiDAR(abstract)；分类 cs.CV

Comments Accepted at AAAI 2024

2303.10076 2023-11-20 cs.CV 89%

A Simple Framework for 3D Occupancy Estimation in Autonomous Driving

Wanshui Gan, Ningkai Mo, Hongbin Xu, Naoto Yokoya

专题命中 BEV与占用：autonomous driving(title,abstract)；occupancy(title,abstract)；BEV(abstract)；分类 cs.CV

Comments 15 pages, 8 figures

2303.09551 2023-08-29 cs.CV 89%

SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving

Yi Wei, Linqing Zhao, Wenzhao Zheng, Zheng Zhu, Jie Zhou, Jiwen Lu

专题命中 BEV与占用：autonomous driving(title,abstract)；occupancy(title,abstract)；LiDAR(abstract)；分类 cs.CV

Comments Accepted to ICCV 2023. Code is available at https://github.com/weiyithu/SurroundOcc

2607.26645 2026-07-30 cs.CV cs.AI 新提交 89%

FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows

FPSGen：基于鸟瞰图支持的传输流的灵活点云场景生成

Wenzhe He, Meng Wang, JiaWei Qian, Jinfeng Xu, Ying Liu, Ruihui Li

专题命中 BEV与占用：BEV(title,summary_cn)；LiDAR(abstract)；分类 cs.CV、cs.AI

AI总结 FPSGen是一种不依赖部分扫描结果的灵活点云场景生成框架，通过BEV先验构建点源与路径拉直传输方案，在SemanticKITTI补全和KITTI-360无条件生成任务上达到先进性能。

Comments 34 pages, 16 figures

2606.22913 2026-06-23 cs.CV cs.AI 新提交 89%

Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving

意图、反思、优化：一种用于自动驾驶的自适应多模态反思框架

Zisheng Chen, Yuping Qiu, Jianhua Han, Tao Tang, Xiuwei Chen, Likui Zhang, Ying-Cong Chen, Hang Xu, Xiaodan Liang

机构 * Sun Yat-sen University（中山大学）； HKUST(GZ)（香港科技大学（广州））； Yinwang Intelligent Technology Co. Ltd.（引望智能科技有限公司）

专题命中 BEV与占用：BEV(summary_cn,abstract)；autonomous driving(title,abstract)；分类 cs.CV、cs.AI

AI总结提出IRR-Drive框架，通过生成初步文本意图并预测未来语义BEV表示，构建双模态反思空间，实现自适应轨迹修正，在NAVSIM基准上达到最优性能。

2302.07817 2023-03-03 cs.CV cs.AI cs.LG 89%

Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction

Yuanhui Huang, Wenzhao Zheng, Yunpeng Zhang, Jie Zhou, Jiwen Lu

专题命中 BEV与占用：occupancy(title,abstract)；autonomous driving(abstract)；BEV(abstract)；LiDAR(abstract)

Comments Accepted to CVPR 2023. Code is available at https://github.com/wzzheng/TPVFormer

2603.09737 2026-03-11 cs.CV cs.RO eess.IV 89%

$M^2$-Occ: Resilient 3D Semantic Occupancy Prediction for Autonomous Driving with Incomplete Camera Inputs

$M^2$-Occ: 用于自动驾驶的不完整摄像机输入下的鲁棒3D语义占位预测

Kaixin Lin, Kunyu Peng, Di Wen, Yufan Chen, Ruiping Liu, Kailun Yang

机构 * School of Artificial Intelligence and Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, China（湖南大学人工智能与机器人学院及机器人视觉感知与控制技术国家工程研究中心，中国）； Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Germany（卡尔斯鲁厄理工学院人机学与机器人研究所，德国）

专题命中 BEV与占用：autonomous driving(title,abstract)；occupancy(title,abstract)；分类 cs.RO、cs.CV、eess.IV

AI总结 $M^2$-Occ通过多视图遮蔽重建和特征记忆模块，在不完整摄像机输入下提升自动驾驶的3D语义占位预测鲁棒性。

Comments The source code will be publicly released at https://github.com/qixi7up/M2-Occ

2305.04205 2023-09-07 cs.CV cs.RO eess.IV 89%

Bi-Mapper: Holistic BEV Semantic Mapping for Autonomous Driving

Siyu Li, Kailun Yang, Hao Shi, Jiaming Zhang, Jiacheng Lin, Zhifeng Teng, Zhiyong Li

专题命中 BEV与占用：autonomous driving(title,abstract)；BEV(title,abstract)；分类 cs.RO、cs.CV、eess.IV

Comments Accepted to IEEE Robotics and Automation Letters (RA-L). The source code is publicly available at https://github.com/lynn-yu/Bi-Mapper

2607.21526 2026-07-24 cs.CV 新提交 89%

Boosting Robustness for All-Weather Self-Supervised Depth Estimation in Autonomous Driving

增强自动驾驶中全天候自监督深度估计的鲁棒性

Mengshi Qi, Xiaoyang Bi, Xianlin Zhang, Huadong Ma

机构 * Beijing University of Posts and Telecommunications（北京邮电大学）

专题命中 BEV与占用：BEV(summary_cn,abstract)；autonomous driving(title,abstract)；分类 cs.CV

AI总结研究自动驾驶中全天候自监督深度估计问题，提出用多教师蒸馏和鲁棒雷达融合的自训练管道，包括不确定性感知多教师蒸馏及POV-BEV雷达融合方法，经实验验证该方法具鲁棒性且性能达最优。

2607.04812 2026-07-07 cs.CV 新提交 89%

TGRIP: A Text-Guided Approach to Vehicle Instance Prediction in Autonomous Driving

TGRIP：一种用于自动驾驶中车辆实例预测的文本引导方法

Miguel Antunes-García, Santiago Montiel-Marín, Fabio Sánchez-García, Rodrigo Gutiérrez-Moreno, Rafael Barea, Luis M. Bergasa

机构 * Electronics Department, University of Alcalá (UAH)（阿尔卡拉大学（UAH）电子系）

专题命中 BEV与占用：autonomous driving(title,abstract)；BEV(abstract,abstract_cn)；occupancy(abstract)；driving perception(abstract)

AI总结研究自动驾驶中鸟瞰图实例预测问题，提出TGRIP框架，利用视觉语言基础模型生成语义增强地图作辅助监督，使网络学习时空表征，提升预测能力。

Comments 11 pages, 5 figures

2606.24784 2026-06-24 cs.CV 新提交 89%

AerialFusionMapNet: Online HD Map Construction with Aerial-Onboard BEV Fusion

AerialFusionMapNet: 基于航拍-车载BEV融合的在线高清地图构建

Daniel Lengerer, Mathias Pechinger, Klaus Bogenberger, Carsten Markgraf

机构 * Technical University of Applied Sciences Augsburg（奥格斯堡应用技术大学）； Technical University of Munich（慕尼黑工业大学）

专题命中 BEV与占用：BEV(title,title_cn)；driving perception(abstract)；分类 cs.CV

AI总结提出AerialFusionMapNet，通过结构化两阶段训练策略有效融合航拍与车载传感器特征，在nuScenes数据集上mAP达54.7，相比基线提升12.1%。

Comments Accepted at the IEEE International Conference on Intelligent Transportation Systems (ITSC) 2026

2511.22039 2026-04-15 cs.CV 89%

SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model

SparseWorld-TC: 基于轨迹的稀疏占用世界模型

Jiayuan Du, Yiming Zhao, Zhenglong Guo, Yong Pan, Wenbo Hou, Zhihui Hao, Kun Zhan, Qijun Chen

机构 * Tongji University（同济大学）； Li Auto Inc（力汽车公司）

专题命中 BEV与占用：BEV(summary_cn,abstract)；occupancy(title,abstract)；分类 cs.CV

AI总结本文提出了一种基于轨迹的未来3D场景占用预测新架构，通过端到端方式直接从原始图像特征预测多帧占用，避免了离散token化和BEV表示的限制，实现了nuScenes基准上的1-3秒占用预测最优性能。

Comments Accepted by CVPR2026 as an oral

2603.17159 2026-03-19 cs.CV cs.RO 88%

BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird's-Eye View Images

BEV-SLD：基于LiDAR鸟瞰图像的自监督场景地标检测用于全局定位

David Skuddis, Vincent Ress, Wei Zhang, Vincent Ofosu Nyako, Norbert Haala

机构 * Institute for Photogrammetry and Geoinformatics, University of Stuttgart, Germany（摄影测量与地理信息研究所，斯图加特大学，德国）

专题命中 BEV与占用：BEV(title,abstract)；LiDAR(title,abstract)；分类 cs.RO、cs.CV

AI总结本文提出BEV-SLD，通过自监督学习利用鸟瞰图像发现特定场景模式，实现鲁棒的全局定位，优于现有方法。

Comments Accepted to CVPR 2026

2407.21126 2025-10-20 cs.CV cs.RO 88%

Self-supervised Multi-future Occupancy Forecasting for Autonomous Driving

Bernard Lange, Masha Itkina, Jiachen Li, Mykel J. Kochenderfer

专题命中 BEV与占用：occupancy(title,abstract)；autonomous driving(title)；LiDAR(abstract)；分类 cs.RO、cs.CV

Comments Accepted to Robotics: Science and Systems (RSS) 2025

2508.06074 2025-08-11 cs.AI cs.RO 88%

ME$^3$-BEV: Mamba-Enhanced Deep Reinforcement Learning for End-to-End Autonomous Driving with BEV-Perception

Siyi Lu, Run Liu, Dongsheng Yang, Lei He

专题命中 BEV与占用：autonomous driving(title,abstract)；BEV(title,abstract)；分类 cs.RO、cs.AI

2508.01778 2025-08-05 cs.CV cs.RO 88%

DiffSemanticFusion: Semantic Raster BEV Fusion for Autonomous Driving via Online HD Map Diffusion

Zhigang Sun, Yiru Wang, Anqing Jiang, Shuo Wang, Yu Gao, Yuwen Heng, Shouyi Zhang, An He, Hao Jiang, Jinhao Chai, Zichong Gu, Wang Jijun, Shichen Tang, Lavdim Halilaj, Juergen Luettin, Hao Sun

机构 * Bosch Corporate Research, Bosch (China) Investment Ltd.（博世企业研究院、博世（中国）投资有限公司）； School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）； Shanghai Jiaotong University（上海交通大学）； AIR, Tsinghua University（清华大学人工智能研究院）； Robert Bosch GmbH（罗伯特·博世集团）

专题命中 BEV与占用：autonomous driving(title,abstract)；BEV(title,abstract)；分类 cs.RO、cs.CV

2401.01065 2024-06-19 cs.CV cs.AI 88%

BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving

Tao Tang, Dafeng Wei, Zhengyu Jia, Tian Gao, Changwei Cai, Chengkai Hou, Peng Jia, Kun Zhan, Haiyang Sun, Jingchen Fan, Yixing Zhao, Fu Liu, Xiaodan Liang, Xianpeng Lang, Yang Wang

专题命中 BEV与占用：autonomous driving(title,abstract)；BEV(title,abstract)；分类 cs.CV、cs.AI

1. BEV与占用 3753 篇

LiDAR-based 4D Occupancy Completion and Forecasting

OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving

BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving

Dr.Occ: Depth- and Region-Guided 3D Occupancy from Surround-View Cameras for Autonomous Driving

DA-Occ: Direction-Aware 2D Convolution for Efficient and Geometry-Preserving 3D Occupancy Prediction in Autonomous Driving

MS-Occ: Multi-Stage LiDAR-Camera Fusion for 3D Semantic Occupancy Prediction

BEV-LLM: Leveraging Multimodal BEV Maps for Scene Captioning in Autonomous Driving

M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving

Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving

MR-Occ: Efficient Camera-LiDAR 3D Semantic Occupancy Prediction Using Hierarchical Multi-Resolution Voxel Representation

Hierarchical End-to-End Autonomous Driving: Integrating BEV Perception with Deep Reinforcement Learning

MambaOcc: Visual State Space Model for BEV-based Occupancy Prediction with Local Adaptive Reordering

OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments

BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios

A Simple Framework for 3D Occupancy Estimation in Autonomous Driving

SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving

FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows

Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving

Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction

$M^2$-Occ: Resilient 3D Semantic Occupancy Prediction for Autonomous Driving with Incomplete Camera Inputs

Bi-Mapper: Holistic BEV Semantic Mapping for Autonomous Driving

Boosting Robustness for All-Weather Self-Supervised Depth Estimation in Autonomous Driving

TGRIP: A Text-Guided Approach to Vehicle Instance Prediction in Autonomous Driving

AerialFusionMapNet: Online HD Map Construction with Aerial-Onboard BEV Fusion

SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model

BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird's-Eye View Images

Self-supervised Multi-future Occupancy Forecasting for Autonomous Driving

ME$^3$-BEV: Mamba-Enhanced Deep Reinforcement Learning for End-to-End Autonomous Driving with BEV-Perception

DiffSemanticFusion: Semantic Raster BEV Fusion for Autonomous Driving via Online HD Map Diffusion

BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving