自动驾驶 - arXivDaily 专题

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

2606.29469 2026-06-30 cs.RO 85%

MTD-Map: Single-Stage Long-Term LiDAR Map Maintenance Framework via Mixture Transition Distribution

MTD-Map：基于混合转移分布的单阶段长期LiDAR地图维护框架

TaeYoung Kim, Gilhwan Kang, Tae Ihn Kim, Seungwon Song, Hun Keon Ko

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

AI总结提出MTD-Map，一种单阶段框架，通过混合转移分布建模同时处理动态物体移除和变化检测，无需独立模块，并采用递归公式和自适应策略平衡噪声抑制与准静态结构保留。

Comments 8 pages, Accepted to IROS 2026

2606.11507 2026-06-11 cs.CV 新提交 85%

SceneMiner: Identity-Preserving Multi-Task Fine-Tuning for Unified BEV Scene Mining

SceneMiner: 保持身份的多任务微调用于统一BEV场景挖掘

Abdalmalek Aburaddaha, Venkatraman Narayanan, Keval Thaker, Samir A. Rawashdeh

机构 * University of Michigan-Dearborn（密歇根大学迪尔伯恩分校）

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

AI总结提出SceneMiner，一种统一的仅相机鸟瞰图管道，通过冻结视觉语言骨干网络在单次前向传播中发出互补的挖掘信号，并发现跨任务干扰问题，通过零初始化新子模块和冻结共享流参数的身份保持多任务微调解决。

2505.10685 2026-02-17 cs.CV 85%

GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attention

GaussianFormer3D: 多模态基于高斯的语义占用预测与3D可变形注意力

Lingjun Zhao, Sizhe Wei, James Hays, Lu Gan

机构 * Georgia Institute of Technology（佐治亚理工学院）

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

AI总结 GaussianFormer3D通过3D可变形注意力机制，结合激光雷达与摄像头数据，实现高效且精确的语义占用预测。

2501.15394 2026-01-21 cs.CV 85%

Doracamom: Joint 3D Detection and Occupancy Prediction with Multi-view 4D Radars and Cameras for Omnidirectional Perception

Doracamom：多视角4D雷达与摄像头联合3D检测与占用预测用于全方位感知

Lianqing Zheng, Jianan Liu, Runwei Guan, Long Yang, Shouyi Lu, Yuanzhe Li, Xiaokai Bai, Jie Bai, Zhixiong Ma, Hui-Liang Shen, Xichan Zhu

机构 * School of Automotive Studies, Tongji University（同济大学汽车学院）； Momoni AI ； Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系）； Chair of Automotive Engineering, Technische Universität Berlin（柏林技术大学汽车工程学系）； College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）； School of Information and Electrical Engineering, Hangzhou City University（杭州城市学院信息与电气工程学院）

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

AI总结 Doracamom通过融合多视角4D雷达与摄像头，实现3D物体检测与语义占用预测，提升自动驾驶环境感知能力。

Comments Accepted by IEEE TCSVT

2512.15311 2025-12-18 cs.CV 85%

KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird's-Eye-View Segmentation

KD360-VoxelBEV: 多模态知识蒸馏用于鸟瞰图分割的激光雷达与360度摄像头交叉模态方法

Wenke E, Yixin Sun, Jiaxu Liu, Hubert P. H. Shum, Amir Atapour-Abarghouei, Toby P. Breckon

机构 * Durham University（杜伦大学）

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

AI总结 KD360-VoxelBEV通过跨模态知识蒸馏，利用激光雷达和360度摄像头数据提升鸟瞰图分割性能，实现高效且低成本的自动驾驶应用。

2512.14225 2025-12-17 cs.CV 85%

OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving

OmniGen：面向自动驾驶的统一多模态传感器生成

Tao Tang, Enhui Ma, xia zhou, Letian Wang, Tianyi Yan, Xueyang Zhang, Kun Zhan, Peng Jia, XianPeng Lang, Jia-Wang Bian, Kaicheng Yu, Xiaodan Liang

机构 * Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）； Westlake University（西湖大学）； Li Auto Inc.（Li汽车公司）； The University of Toronto（多伦多大学）； University of Macau（澳门大学）

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

AI总结 OmniGen通过统一框架生成对齐的多模态传感器数据，结合共享BEV空间和UAE方法，实现高效且灵活的传感器生成。

Comments ACM MM 2025

2501.16480 2025-11-18 cs.RO cs.LG eess.SP 85%

Dynamic Risk Assessment for Autonomous Vehicles from Spatio-Temporal Probabilistic Occupancy Heatmaps

Han Wang, Yuneil Yeo, Antonio R. Paiva, Jean Utke, Maria Laura Delle Monache

机构 * Department of Civil and Environmental Engineering, University of California, Berkeley, CA, USA（加州大学伯克利分校土木与环境工程系）； D3 Analytics Innovation, Allstate Insurance Company, Northbrook, IL, USA（Allstate保险公司D3 Analytics创新部门）； Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA（加州大学伯克利分校电气工程与计算机科学系）

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

2505.13817 2025-09-24 cs.CV 85%

InstanceBEV: Unifying Instance and BEV Representation for 3D Panoptic Segmentation

Feng Li, Zhaoyue Wang, Enyuan Zhang, Mohammad Masum Billah, Yunduan Cui, Kun Xu

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

2509.03999 2025-09-05 cs.CV 85%

SliceSemOcc: Vertical Slice Based Multimodal 3D Semantic Occupancy Representation

Han Huang, Han Sun, Ningzhong Liu, Huiyu Zhou, Jiaquan Shen

机构 * Nanjing University of Aeronautics and Astronautics（南京航空航天大学）； University of Leicester（莱斯特大学）； Luoyang Normal University（洛阳师范学院）

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

Comments 14 pages, accepted by PRCV2025

2502.17288 2025-08-26 cs.CV 85%

GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow

Simon Boeder, Fabian Gigengack, Benjamin Risse

机构 * Robert Bosch GmbH（罗伯特·博世有限公司）； University of Münster（穆斯尔大学）

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

Comments Accepted to ICCV 2025

2507.21358 2025-08-05 cs.CV 85%

Collaborative Perceiver: Elevating Vision-based 3D Object Detection via Local Density-Aware Spatial Occupancy

Jicheng Yuan, Manh Nguyen Duc, Qian Liu, Manfred Hauswirth, Danh Le Phuoc

机构 * The Open Distributed Systems (ODS) Group at the Technische Universität Berlin（技术大学柏林开放分布式系统（ODS）小组）； Fraunhofer FOKUS (Berlin, Germany)（弗劳恩霍夫研究所FOKUS（柏林，德国））

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

Comments The manuscript has been accepted by ICONIP2025

2507.19451 2025-08-05 cs.CV 85%

GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting

Baijun Ye, Minghui Qin, Saining Zhang, Moonjun Gong, Shaoting Zhu, Zebang Shen, Luan Zhang, Lu Zhang, Hao Zhao, Hang Zhao

机构 * IIIS, THU（清华大学人工智能学院）； Shanghai Qi Zhi Institute（上海启智研究院）； AIR, THU（清华大学人工智能研究院）； BAAI（北京人工智能研究院）； Mercedes-Benz Group China Ltd.（梅赛德斯-奔驰集团中国有限公司）

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

Comments ICCV 2025. Project Page: https://gs-occ3d.github.io/

2309.10527 2025-07-17 cs.CV 85%

SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations

Xiangchao Yan, Runjian Chen, Bo Zhang, Hancheng Ye, Renqiu Xia, Jiakang Yuan, Hongbin Zhou, Xinyu Cai, Botian Shi, Wenqi Shao, Ping Luo, Yu Qiao, Tao Chen, Junchi Yan

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； The University of Hong Kong（香港大学）； School of Information Science and Technology（信息科学与技术学院）； Fudan University（复旦大学）； School of Artificial Intelligence（人工智能学院）； Shanghai Jiao Tong University（上海交通大学）

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

Comments SPOT has been accepted as a Regular Paper in T-PAMI, and code is available at https://github.com/PJLab-ADG/3DTrans

2405.10591 2025-03-25 cs.CV 85%

GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision

Xin Tan, Wenbin Wu, Zhiwei Zhang, Chaojie Fan, Yong Peng, Zhizhong Zhang, Yuan Xie, Lizhuang Ma

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

Comments This work has been accepted for publication in IEEE Transactions on Intelligent Transportation Systems

Journal ref IEEE Transactions on Intelligent Transportation Systems, pp. 1-12, March 2025

2412.05435 2025-03-12 cs.CV 85%

UniScene: Unified Occupancy-centric Driving Scene Generation

Bohan Li, Jiazhe Guo, Hongsi Liu, Yingshuang Zou, Yikang Ding, Xiwu Chen, Hu Zhu, Feiyang Tan, Chi Zhang, Tiancai Wang, Shuchang Zhou, Li Zhang, Xiaojuan Qi, Hao Zhao, Mu Yang, Wenjun Zeng, Xin Jin

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

Comments CVPR 2025

2501.16684 2025-01-29 cs.CV 85%

SliceOcc: Indoor 3D Semantic Occupancy Prediction with Vertical Slice Representation

Jianing Li, Ming Lu, Hao Wang, Chenyang Gu, Wenzhao Zheng, Li Du, Shanghang Zhang

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

Comments Accepted by ICRA 2025;

2411.12452 2024-11-20 cs.CV 85%

GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous Driving

Shaoqing Xu, Fang Li, Shengyin Jiang, Ziying Song, Li Liu, Zhi-xin Yang

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

Comments 10 pages, 5 figures

2411.03696 2024-11-07 cs.CV 85%

OccLoff: Learning Optimized Feature Fusion for 3D Occupancy Prediction

Ji Zhang, Yiran Ding, Zixin Liu

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

2408.10880 2024-08-21 cs.CV 85%

Open 3D World in Autonomous Driving

Xinlong Cheng, Lei Li

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

2407.17310 2024-07-26 cs.CV 85%

LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Rendering

Simon Boeder, Fabian Gigengack, Benjamin Risse

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

2407.13155 2024-07-23 cs.CV 85%

Real-Time 3D Occupancy Prediction via Geometric-Semantic Disentanglement

Yulin He, Wei Chen, Tianci Xun, Yusong Tan

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

2407.11682 2024-07-17 cs.CV 85%

MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation

Xiaoshuai Hao, Ruikai Li, Hui Zhang, Dingzhe Li, Rong Yin, Sangil Jung, Seung-In Park, ByungIn Yoo, Haimei Zhao, Jing Zhang

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

Comments Accepted by ECCV2024

2405.16099 2024-05-28 cs.CV 85%

Improving 3D Occupancy Prediction through Class-balancing Loss and Multi-scale Representation

Huizhou Chen, Jiangyi Wang, Yuxin Li, Na Zhao, Jun Cheng, Xulei Yang

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

Comments 5 pages, 3 figures, accepted by IEEE CAI 2024

2404.04561 2024-05-24 cs.CV 85%

Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Prediction

Jingyi Pan, Zipeng Wang, Lin Wang

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

Comments Accepted by IEEE Robotics and Automation Letters (RA-L)

Journal ref IEEE Robotics and Automation Letters, Volume 9 Issue 6, 5687 - 5694, June 2024

2404.09502 2024-04-16 cs.CV 85%

SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction

Pin Tang, Zhongdao Wang, Guoqing Wang, Jilai Zheng, Xiangxuan Ren, Bailan Feng, Chao Ma

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

Comments 10 pages, 4 figures, accepted by CVPR 2024

Journal ref IEEE Conference on Computer Vision and Pattern Recognition 2024 (CVPR 2024)

2402.15583 2024-02-27 cs.CV cs.LG 85%

Cohere3D: Exploiting Temporal Coherence for Unsupervised Representation Learning of Vision-based Autonomous Driving

Yichen Xie, Hongge Chen, Gregory P. Meyer, Yong Jae Lee, Eric M. Wolff, Masayoshi Tomizuka, Wei Zhan, Yuning Chai, Xin Huang

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

2311.12058 2023-11-22 cs.CV 85%

FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin

Zichen Yu, Changyong Shu, Jiajun Deng, Kangjie Lu, Zongdai Liu, Jiangyong Yu, Dawei Yang, Hui Li, Yan Chen

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

Comments 10 pages, 4 figures

2204.05727 2023-05-18 cs.RO 85%

LiDAR Road-Atlas: An Efficient Map Representation for General 3D Urban Environment

Banghe Wu, Chengzhong Xu, Hui Kong

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

Journal ref Field Robotics, 2023

2303.17099 2023-03-31 cs.CV 85%

BEVFusion4D: Learning LiDAR-Camera Fusion Under Bird's-Eye-View via Cross-Modality Guidance and Temporal Aggregation

Hongxiang Cai, Zeyuan Zhang, Zhenyu Zhou, Ziyin Li, Wenbo Ding, Jiuhua Zhao

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

Comments 13 pages, 7 figures

1. BEV与占用 3755 篇

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

MTD-Map: Single-Stage Long-Term LiDAR Map Maintenance Framework via Mixture Transition Distribution

SceneMiner: Identity-Preserving Multi-Task Fine-Tuning for Unified BEV Scene Mining

GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attention

Doracamom: Joint 3D Detection and Occupancy Prediction with Multi-view 4D Radars and Cameras for Omnidirectional Perception

KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird's-Eye-View Segmentation

OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving

Dynamic Risk Assessment for Autonomous Vehicles from Spatio-Temporal Probabilistic Occupancy Heatmaps

InstanceBEV: Unifying Instance and BEV Representation for 3D Panoptic Segmentation

SliceSemOcc: Vertical Slice Based Multimodal 3D Semantic Occupancy Representation

GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow

Collaborative Perceiver: Elevating Vision-based 3D Object Detection via Local Density-Aware Spatial Occupancy

GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting

SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations

GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision

UniScene: Unified Occupancy-centric Driving Scene Generation

SliceOcc: Indoor 3D Semantic Occupancy Prediction with Vertical Slice Representation

GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous Driving

OccLoff: Learning Optimized Feature Fusion for 3D Occupancy Prediction

Open 3D World in Autonomous Driving

LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Rendering

Real-Time 3D Occupancy Prediction via Geometric-Semantic Disentanglement

MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation

Improving 3D Occupancy Prediction through Class-balancing Loss and Multi-scale Representation

Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Prediction

SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction

Cohere3D: Exploiting Temporal Coherence for Unsupervised Representation Learning of Vision-based Autonomous Driving

FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin

LiDAR Road-Atlas: An Efficient Map Representation for General 3D Urban Environment

BEVFusion4D: Learning LiDAR-Camera Fusion Under Bird's-Eye-View via Cross-Modality Guidance and Temporal Aggregation