自动驾驶 - arXivDaily 专题

2603.02609 2026-03-04 cs.CV cs.RO 86%

VLMFusionOcc3D: VLM Assisted Multi-Modal 3D Semantic Occupancy Prediction

VLMFusionOcc3D: 基于VLM的多模态3D语义占位预测

A. Enes Doruk, Hasan F. Ates

机构 * Department of Artificial Intelligence and Data Engineering, Ozyegin University（人工智能与数据工程系，奥克辛大学）

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

AI总结 VLMFusionOcc3D通过融合视觉语言模型的语义先验，提升多模态3D语义占位预测的鲁棒性和适应性。

2507.13387 2025-12-24 cs.CV eess.IV 86%

From Binary to Semantic: Utilizing Large-Scale Binary Occupancy Data for 3D Semantic Occupancy Prediction

从二元到语义：利用大规模二元占用数据进行3D语义占用预测

Chihiro Noguchi, Takaki Yamamoto

机构 * InfoTech, Toyota Motor Corporation（丰田汽车公司信息科技部）

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

AI总结本文提出一种基于二元占用数据的框架，通过预训练和自动标注方法提升3D语义占用预测的性能。

Comments Accepted to ICCV Workshop 2025

2511.16949 2025-11-24 cs.RO cs.CV 86%

MobileOcc: A Human-Aware Semantic Occupancy Dataset for Mobile Robots

MobileOcc: 一种面向移动机器人的人感知语义占用数据集

Junseo Kim, Guido Dumont, Xinyu Gao, Gang Chen, Holger Caesar, Javier Alonso-Mora

机构 * Delft University of Technology（代尔夫特理工大学）

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

AI总结 MobileOcc提出了一种面向移动机器人的人感知语义占用数据集，通过结合静态物体注释和新型网格优化框架，实现了对变形人体几何的重建与优化，并用于建立占用预测和行人速度预测的基准测试。

2506.02587 2025-10-14 cs.CV cs.RO 86%

BEVCALIB: LiDAR-Camera Calibration via Geometry-Guided Bird's-Eye View Representations

Weiduo Yuan, Jerry Li, Justin Yue, Divyank Shah, Konstantinos Karydis, Hang Qiu

机构 * University of Southern California（南加州大学）； University of California, Riverside（加州大学河滨分校）

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

Journal ref 9th Conference on Robot Learning (CoRL 2025), Seoul, Korea

2509.05578 2025-09-09 cs.AI cs.RO 86%

OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision

Ruixun Liu, Lingyu Kong, Derun Li, Hang Zhao

机构 * Shanghai Qi Zhi Institute（上海启智研究所）； Xi’an Jiaotong University（西安交通大学）； Fudan University（复旦大学）； Shanghai Jiao Tong University（上海交通大学）； Tsinghua University（清华大学）

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

2501.15384 2025-08-11 cs.CV cs.AI 86%

MetaOcc: Spatio-Temporal Fusion of Surround-View 4D Radar and Camera for 3D Occupancy Prediction with Dual Training Strategies

Long Yang, Lianqing Zheng, Wenjin Ai, Minghao Liu, Sen Li, Qunshu Lin, Shengyu Yan, Jie Bai, Zhixiong Ma, Tao Huang, Xichan Zhu

机构 * School of Automotive Studies, Tongji University（同济大学汽车学院）； College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）； School of Automobile, Chang'an University（长安大学汽车学院）； School of Information and Electrical Engineering, Hangzhou City University（杭州城市学院信息与电气工程学院）； College of Science and Engineering, James Cook University（詹姆斯库克大学科学与工程学院）

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

2507.17083 2025-07-24 cs.CV cs.AI 86%

SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction

Zaipeng Duan, Chenxu Dang, Xuzhong Hu, Pei An, Junfeng Ding, Jie Zhan, Yunbiao Xu, Jie Ma

机构 * Huazhong University of Science and Technology（华中科技大学）

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

Comments accepted by CVPR2025

2504.02270 2025-04-04 cs.CV cs.RO 86%

MinkOcc: Towards real-time label-efficient semantic occupancy prediction

Samuel Sze, Daniele De Martini, Lars Kunze

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

Comments 8 pages

2409.19987 2025-02-18 cs.CV cs.RO 86%

OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity

Junming Wang, Wei Yin, Xiaoxiao Long, Xingyu Zhang, Zebin Xing, Xiaoyang Guo, Qian Zhang

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

Comments ICRA 2025

2502.04377 2025-02-10 cs.CV cs.AI 86%

MapFusion: A Novel BEV Feature Fusion Network for Multi-modal Map Construction

Xiaoshuai Hao, Yunfeng Diao, Mengchuan Wei, Yifan Yang, Peng Hao, Rong Yin, Hui Zhang, Weiming Li, Shu Zhao, Yu Liu

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

2412.07163 2024-12-11 cs.CV cs.AI 86%

Fast Occupancy Network

Mingjie Lu, Yuanxian Huang, Ji Liu, Xingliang Huang, Dong Li, Jinzhang Peng, Lu Tian, Emad Barsoum

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

Comments 10 pages, 5 figures,

2410.20969 2024-10-29 cs.RO cs.CV 86%

BEVPose: Unveiling Scene Semantics through Pose-Guided Multi-Modal BEV Alignment

Mehdi Hosseinzadeh, Ian Reid

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

Comments Accepted for presentation at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024. Project page: https://m80hz.github.io/bevpose/

2409.18026 2024-09-27 cs.CV cs.RO 86%

ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learning

Song Wang, Zhongdao Wang, Jiawei Yu, Wentong Li, Bailan Feng, Junbo Chen, Jianke Zhu

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

Comments Technical report. Work in progress

2409.00923 2024-09-04 cs.RO cs.AI 86%

Development of Occupancy Prediction Algorithm for Underground Parking Lots

Shijie Wang

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

2403.08748 2024-05-21 cs.RO cs.CV 86%

Real-time 3D semantic occupancy prediction for autonomous vehicles using memory-efficient sparse convolution

Samuel Sze, Lars Kunze

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

Comments 8 pages, 7 figures

2401.12422 2024-04-30 cs.CV cs.RO 86%

InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Prediction

Zhenxing Ming, Julie Stephany Berrio, Mao Shan, Stewart Worrall

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

2402.13848 2024-03-26 cs.CV cs.RO 86%

Zero-BEV: Zero-shot Projection of Any First-Person Modality to BEV Maps

Gianluca Monaci, Leonid Antsfeld, Boris Chidlovskii, Christian Wolf

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

2403.02710 2024-03-06 cs.CV cs.RO 86%

FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective View

Jiawei Hou, Xiaoyan Li, Wenhao Guan, Gang Zhang, Di Feng, Yuheng Du, Xiangyang Xue, Jian Pu

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

Comments Accepted by ICRA 2024

2308.16896 2023-09-01 cs.CV cs.AI cs.LG 86%

PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction

Sicheng Zuo, Wenzhao Zheng, Yuanhui Huang, Jie Zhou, Jiwen Lu

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

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

2304.11379 2023-06-06 cs.CV cs.RO 86%

LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation

Song Wang, Wentong Li, Wenyu Liu, Xiaolu Liu, Jianke Zhu

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

Comments Accepted by CVPR2023

2304.11393 2023-04-25 cs.CV cs.AI 86%

Knowledge Distillation from 3D to Bird's-Eye-View for LiDAR Semantic Segmentation

Feng Jiang, Heng Gao, Shoumeng Qiu, Haiqiang Zhang, Ru Wan, Jian Pu

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

Comments ICME 2023 Accepted

2210.01917 2022-10-19 cs.CV cs.RO 86%

Differentiable Raycasting for Self-supervised Occupancy Forecasting

Tarasha Khurana, Peiyun Hu, Achal Dave, Jason Ziglar, David Held, Deva Ramanan

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

Comments ECCV 2022. Code available at https://github.com/tarashakhurana/emergent-occ-forecasting

2205.05551 2022-05-12 cs.CV cs.RO 86%

NMR: Neural Manifold Representation for Autonomous Driving

Unnikrishnan R. Nair, Sarthak Sharma, Midhun S. Menon, Srikanth Vidapanakal

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

2009.09308 2020-09-22 cs.RO cs.AI 86%

What is the Best Grid-Map for Self-Driving Cars Localization? An Evaluation under Diverse Types of Illumination, Traffic, and Environment

Filipe Mutz, Thiago Oliveira-Santos, Avelino Forechi, Karin S. Komati, Claudine Badue, Felipe M. G. França, Alberto F. De Souza

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

2007.00164 2020-07-02 cs.CV cs.LG cs.RO 86%

Online Domain Adaptation for Occupancy Mapping

Anthony Tompkins, Ransalu Senanayake, Fabio Ramos

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

Comments Robotics: Science and Systems (RSS) 2020 conference

2506.07002 2026-04-07 cs.CV 86%

BePo: Dual Representation for 3D Occupancy Prediction

BePo：3D占用预测的双表示

Yunxiao Shi, Hong Cai, Jisoo Jeong, Yinhao Zhu, Shizhong Han, Amin Ansari, Fatih Porikli

机构 * Qualcomm AI Research（高通人工智能研究院）； Qualcomm Technologies, Inc.（高通技术公司）

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

AI总结本文提出BePo，通过结合BEV和稀疏点的双表示，解决小物体和大平面的占用预测问题，实验表明其在多个基准上表现优异且推理成本低。

Comments CVPR 2026 Workshop on Autonomous Driving

2401.13785 2025-02-18 cs.CV 86%

A Spatiotemporal Approach to Tri-Perspective Representation for 3D Semantic Occupancy Prediction

Sathira Silva, Savindu Bhashitha Wannigama, Gihan Jayatilaka, Muhammad Haris Khan, Roshan Ragel

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

Comments Accepted to the 2025 Workshop on Machine Learning for Autonomous Driving at AAAI

2306.04939 2023-06-09 cs.RO 86%

UAP-BEV: Uncertainty Aware Planning using Bird's Eye View generated from Surround Monocular Images

Vikrant Dewangan, Basant Sharma, Tushar Choudhary, Sarthak Sharma, Aakash Aanegola, Arun K. Singh, K. Madhava Krishna

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

Comments Accepted to CASE 2023. Project video available at https://vikr-182.github.io/UAP-BEV

2602.20575 2026-07-21 cs.CV 版本更新 85%

An interactive enhanced driving dataset for autonomous driving

一种交互增强的自动驾驶数据集

Haojie Feng, Xinrui Zhang, Mengjie Tian, Peizhi Zhang, Zhuoren Li, Junpeng Huang, Xiurong Wang, Junfan Zhu, Jianzhou Wang, Dongxiao Yin, Lu Xiong

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

AI总结本文提出交互增强驾驶数据集，通过生成合成视频实现多模态对齐，用于评估和优化自动驾驶模型的推理能力。

Comments Accepted for publication in Scientific Data

2603.27044 2026-07-07 cs.LG cs.AI 版本更新 85%

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching

无监督行为压缩：通过状态占用匹配学习低维策略流形

Andrea Fraschini, Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli

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

AI总结本文提出Occupancy-based Policy Compression方法，通过改进策略压缩框架，以长周期状态空间覆盖替代即时动作匹配，提升行为表示的鲁棒性和泛化能力。

Comments RLC 2026 camera-ready version

1. BEV与占用 3753 篇

VLMFusionOcc3D: VLM Assisted Multi-Modal 3D Semantic Occupancy Prediction

From Binary to Semantic: Utilizing Large-Scale Binary Occupancy Data for 3D Semantic Occupancy Prediction

MobileOcc: A Human-Aware Semantic Occupancy Dataset for Mobile Robots

BEVCALIB: LiDAR-Camera Calibration via Geometry-Guided Bird's-Eye View Representations

OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision

MetaOcc: Spatio-Temporal Fusion of Surround-View 4D Radar and Camera for 3D Occupancy Prediction with Dual Training Strategies

SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction

MinkOcc: Towards real-time label-efficient semantic occupancy prediction

OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity

MapFusion: A Novel BEV Feature Fusion Network for Multi-modal Map Construction

Fast Occupancy Network

BEVPose: Unveiling Scene Semantics through Pose-Guided Multi-Modal BEV Alignment

ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learning

Development of Occupancy Prediction Algorithm for Underground Parking Lots

Real-time 3D semantic occupancy prediction for autonomous vehicles using memory-efficient sparse convolution

InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Prediction

Zero-BEV: Zero-shot Projection of Any First-Person Modality to BEV Maps

FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective View

PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction

LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation

Knowledge Distillation from 3D to Bird's-Eye-View for LiDAR Semantic Segmentation

Differentiable Raycasting for Self-supervised Occupancy Forecasting

NMR: Neural Manifold Representation for Autonomous Driving

What is the Best Grid-Map for Self-Driving Cars Localization? An Evaluation under Diverse Types of Illumination, Traffic, and Environment

Online Domain Adaptation for Occupancy Mapping

BePo: Dual Representation for 3D Occupancy Prediction

A Spatiotemporal Approach to Tri-Perspective Representation for 3D Semantic Occupancy Prediction

UAP-BEV: Uncertainty Aware Planning using Bird's Eye View generated from Surround Monocular Images

An interactive enhanced driving dataset for autonomous driving

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching