arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

自动驾驶

自动驾驶感知、规划、BEV、占用预测、激光雷达和仿真评测。

共收录 3753 信号源:cs.RO, cs.CV, eess.IV, cs.AI

1. BEV与占用 3753 篇

2607.04732 2026-07-07 cs.CV 新提交 87%

SparseOcc++: Geometry-Aware Sparse Latent Representation for Semantic Occupancy Prediction

SparseOcc++:用于语义占用预测的几何感知稀疏潜在表示

Pin Tang, Zhongdao Wang, Guoqing Wang, Xiangxuan Ren, Chao Ma

机构 * MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University(教育部人工智能重点实验室,上海交通大学人工智能研究院) Huawei Noah’s Ark Lab(华为诺亚方舟实验室)

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

AI总结 研究针对基于视觉的3D语义占用预测,提出SparseOcc++框架,通过场景完成场将场景完成与语义分割解耦,用新方法建模复杂户外几何,实验表明其提升了IoU且速度更快。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.24051 2026-06-24 cs.CV 新提交 87%

DriveStack-VLA: Render-Teacher Alignment for BEV-Based DeepStack Vision-Language-Action Model

DriveStack-VLA: 基于BEV的DeepStack视觉-语言-动作模型的渲染-教师对齐

Jingke Wang, Zhenru Zhao, Shuangming Lei, Hao Su, Yuehao Huang, Yijia Xie, Kai Tang, Guanglin Xu, AiXue Ye, Yukai Ma, Yong Liu

机构 * Zhejiang University(浙江大学) The 2012 Labs, Huawei(华为2012实验室)

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

AI总结 提出DriveStack-VLA框架,通过DeepStack连接注入BEV表示并采用渲染-教师对齐增强空间感知,引入自批评模块优化轨迹选择,在多个驾驶基准上取得领先性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.05976 2026-06-23 cs.CV 版本更新 87%

LightOcc: Lightweight Spatial Embedding for Efficient Vision-based 3D Occupancy Prediction

LightOcc: 用于高效基于视觉的3D占用预测的轻量级空间嵌入

Jinqing Zhang, Yanan Zhang, Wenrui Cai, Qingjie Liu, Yunhong Wang

机构 * State Key Laboratory of Virtual Reality Technology and Systems(虚拟现实技术与系统国家重点实验室) Beihang University(北京航空航天大学) School of Computer Science and Information Engineering(计算机科学与信息工程学院) Hefei University of Technology(合肥工业大学) Hangzhou Innovation Institute(杭州创新研究院)

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

AI总结 针对现有占用预测方法使用体素特征导致计算和内存开销大的问题,提出轻量级空间嵌入(Lightweight Spatial Embedding),通过单通道占用和空间到通道机制压缩高度信息,结合跨视图交互和边缘感知嵌入,在多个基准上实现最先进性能并显著提升效率。

Comments Accepted by International Journal of Computer Vision (IJCV), 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.22852 2026-03-25 cs.CV 87%

Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction

Gau-Occ:用于多模态3D占用预测的几何完备高斯分布

Chengxin Lv, Yihui Li, Hongyu Yang, YunHong Wang

机构 * State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China(虚拟现实技术与系统国家重点实验室,北京航空航天大学,北京,中国) School of Computer Science and Engineering, Beihang University, Beijing, China(计算机科学与工程学院,北京航空航天大学,北京,中国) School of Artificial Intelligence, Beihang University, Beijing, China(人工智能学院,北京航空航天大学,北京,中国)

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

AI总结 Gau-Occ通过几何完备的3D高斯分布实现多模态3D占用预测,利用LiDAR完成扩散器恢复缺失结构并融合多视角图像语义,提升空间一致性和语义区分性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16729 2026-02-10 cs.CV 87%

Vision-Centric 4D Occupancy Forecasting and Planning via Implicit Residual World Models

基于隐式残差世界模型的视觉导向4D占用预测与规划

Jianbiao Mei, Yu Yang, Xuemeng Yang, Licheng Wen, Jiajun Lv, Botian Shi, Yong Liu

机构 * Zhejiang University(浙江大学) Shanghai AI Laboratory(上海人工智能实验室)

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

AI总结 本文提出IR-WM,通过隐式残差世界模型提升自动驾驶中的4D占用预测与轨迹规划精度。

Comments ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.22729 2026-02-02 cs.CV 87%

GaussianOcc3D: A Gaussian-Based Adaptive Multi-modal 3D Occupancy Prediction

GaussianOcc3D: 一种基于高斯的自适应多模态3D占用预测

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,奥祖根大学)

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

AI总结 GaussianOcc3D通过高斯表示实现多模态3D占用预测,提升自动驾驶环境感知的鲁棒性和精度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.20617 2026-01-23 cs.CV 87%

OccLE: Label-Efficient 3D Semantic Occupancy Prediction

OccLE:高效标注的3D语义占用预测

Naiyu Fang, Zheyuan Zhou, Fayao Liu, Xulei Yang, Jiacheng Wei, Lemiao Qiu, Hongsheng Li, Guosheng Lin

机构 * NTU, S-Lab(国立科技大学,S-Lab) ZJU(浙江大学) A*STAR(A*STAR研究所) NTU, CCDS(国立科技大学,CCDS) CUHK, MMLab(香港中文大学,MMLab)

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

AI总结 OccLE通过解耦语义和几何学习任务,利用半监督和双Mamba融合技术,在有限标注下实现高效的3D语义占用预测。

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.07367 2025-03-11 cs.CV 87%

LEGO-Motion: Learning-Enhanced Grids with Occupancy Instance Modeling for Class-Agnostic Motion Prediction

Kangan Qian, Jinyu Miao, Ziang Luo, Zheng Fu, and Jinchen Li, Yining Shi, Yunlong Wang, Kun Jiang, Mengmeng Yang, Diange Yang

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

Comments 8 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.12177 2024-11-20 cs.CV 87%

Robust 3D Semantic Occupancy Prediction with Calibration-free Spatial Transformation

Zhuangwei Zhuang, Ziyin Wang, Sitao Chen, Lizhao Liu, Hui Luo, Mingkui Tan

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

Comments 13 pages, 11 figures, 18 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2302.09585 2024-06-12 cs.CV 87%

StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation

Yining Shi, Kun Jiang, Ke Wang, Jiusi Li, Yunlong Wang, Mengmeng Yang, Diange Yang

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

Comments cvpr2024 poster (highlight), code at https://github.com/synsin0/StreamingFlow

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.15660 2023-11-28 cs.CV 87%

Technical Report for Argoverse Challenges on 4D Occupancy Forecasting

Pengfei Zheng, Kanokphan Lertniphonphan, Feng Chen, Siwei Chen, Bingchuan Sun, Jun Xie, Zhepeng Wang

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2304.05316 2023-04-12 cs.CV 87%

OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction

Yunpeng Zhang, Zheng Zhu, Dalong Du

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

Comments Code is available at https://github.com/zhangyp15/OccFormer

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.25728 2026-07-29 cs.RO cs.AI cs.LG 新提交 87%

Shared Voxel-Map-Based Cooperative Indoor UAV Guidance with a Multi-Agent Soft Actor-Critic Controller

基于共享体素地图的多智能体软演员-评论家控制器协同室内无人机导航

Thomas Hickling, Dylan Wynne, Yu Su, Nabil Aouf

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

AI总结 研究室内无人机协同导航问题,提出结合共享体素地图与多智能体软演员-评论家控制器的框架,多无人机融合LiDAR观测构建地图并提供给各智能体,模拟中控制器成功率达90.3%,经微调后在现实实验中实现稳定协同操作,证明该地图表示有效且可扩展。

Comments 11 pages, 17 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.26113 2026-05-26 cs.RO cs.CV 87%

AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond

AnyScene: 迈向高度可控的任意位置驾驶场景生成及超越

Haiming Zhang, Junfei Zhou, Feng Jiang, Jingzhong Li, Zhenglong Guo, Penglin Dai, Jifeng Dai, Yan Xie, Benjin Zhu

机构 * Li Auto(利汽车) Southwest Jiaotong University(西南交通大学) Tsinghua University(清华大学)

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

AI总结 提出AnyScene框架,通过时空占用扩散Transformer和几何引导视图扩展模块,实现从BEV布局生成语义占用序列和参考无关的多视角驾驶视频,支持精确可控和长时生成。

Comments Work in progress. Project page: https://mind-omni.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.01023 2025-04-03 cs.CV cs.RO 87%

Omnidirectional Depth-Aided Occupancy Prediction based on Cylindrical Voxel for Autonomous Driving

Chaofan Wu, Jiaheng Li, Jinghao Cao, Ming Li, Yongkang Feng, Jiayu Wu Shuwen Xu, Zihang Gao, Sidan Du, Yang Li

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2208.00394 2023-07-07 cs.CV cs.AI 87%

STrajNet: Multi-modal Hierarchical Transformer for Occupancy Flow Field Prediction in Autonomous Driving

Haochen Liu, Zhiyu Huang, Chen Lv

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.21185 2026-01-13 cs.CV cs.RO eess.IV 87%

Out-of-Distribution Semantic Occupancy Prediction

分布外语义占用预测

Yuheng Zhang, Mengfei Duan, Kunyu Peng, Yuhang Wang, Ruiping Liu, Fei Teng, Kai Luo, Zhiyong Li, Kailun Yang

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

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

AI总结 本文提出OccOoD框架,通过跨空间语义细化提升3D语义占用预测中的分布外检测性能。

Comments The established datasets and source code will be made publicly available at https://github.com/7uHeng/OccOoD

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.18798 2025-08-14 cs.CV cs.AI cs.RO 87%

OC-SOP: Enhancing Vision-Based 3D Semantic Occupancy Prediction by Object-Centric Awareness

Helin Cao, Sven Behnke

机构 * Autonomous Intelligent Systems group, Computer Science Institute VI – Intelligent Systems and Robotics – and the Center for Robotics and the Lamarr Institute for Machine Learning and Artificial Intelligence, University of Bonn, Germany(自主智能系统组,计算机科学研究所VI——智能系统与机器人——以及机器人中心和拉玛尔人工智能与机器学习研究所,波恩大学,德国)

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

Comments 2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Vienna, Austria, Oct 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.12409 2024-10-22 cs.CV cs.AI cs.RO 87%

Deep Radar Inverse Sensor Models for Dynamic Occupancy Grid Maps

Zihang Wei, Rujiao Yan, Matthias Schreier

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.03724 2024-06-13 cs.CV cs.AI cs.RO 87%

DualCross: Cross-Modality Cross-Domain Adaptation for Monocular BEV Perception

Yunze Man, Liang-Yan Gui, Yu-Xiong Wang

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

Comments IROS 2023. Project website: https://yunzeman.github.io/DualCross

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.04503 2026-04-28 cs.CV cs.RO 87%

U-ViLAR: Uncertainty-Aware Visual Localization for Autonomous Driving via Differentiable Association and Registration

U-ViLAR:基于可微关联和注册的不确定性感知视觉定位

Xiaofan Li, Zhihao Xu, Chenming Wu, Zhao Yang, Yumeng Zhang, Jiang-Jiang Liu, Haibao Yu, Fan Duan, Xiaoqing Ye, Yuan Wang, Shirui Li, Xun Sun, Ji Wan, Jun Wang

机构 * Baidu Inc.(百度公司)

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

AI总结 U-ViLAR通过可微关联和注册方法,提升自动驾驶中视觉定位的鲁棒性和精度,实验表明其在多种定位任务中表现优异。

Comments Vision Localization, Autonomous Driving, Bird's-Eye-View

详情

展开后加载摘要…

URL PDF HTML 收藏
2307.01492 2023-07-06 cs.CV cs.RO 87%

FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation

Zhiqi Li, Zhiding Yu, David Austin, Mingsheng Fang, Shiyi Lan, Jan Kautz, Jose M. Alvarez

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

Comments Outstanding Champion and Innovation Award in the 3D Occupancy Prediction Challenge (CVPR23)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.31177 2026-07-01 cs.CV 新提交 86%

GaussianMap: Learning Gaussian Representation for Multi-Sensor Online HD Map Construction

GaussianMap: 学习高斯表示用于多传感器在线高清地图构建

Hongyu Lyu, Julie Stephany Berrio Perez, Mao Shan, Stewart Worrall

机构 * The University of Sydney, Australian Centre for Robotics(悉尼大学澳大利亚机器人中心) The University of Queensland(昆士兰大学)

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

AI总结 提出GaussianMap框架,利用自适应高斯表示代替固定分辨率BEV网格,通过高斯编码器与多传感器融合,实现高效在线高清地图构建,在nuScenes和Argoverse 2上达到SOTA。

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.01723 2024-04-15 cs.RO 86%

Predicting Future Spatiotemporal Occupancy Grids with Semantics for Autonomous Driving

Maneekwan Toyungyernsub, Esen Yel, Jiachen Li, Mykel J. Kochenderfer

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

Comments Accepted at the 35th IEEE Intelligent Vehicles Symposium 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2309.11011 2024-03-27 cs.RO 86%

OCC-VO: Dense Mapping via 3D Occupancy-Based Visual Odometry for Autonomous Driving

Heng Li, Yifan Duan, Xinran Zhang, Haiyi Liu, Jianmin Ji, Yanyong Zhang

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

Comments 7pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2304.14365 2023-12-14 cs.CV 86%

Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving

Xiaoyu Tian, Tao Jiang, Longfei Yun, Yucheng Mao, Huitong Yang, Yue Wang, Yilun Wang, Hang Zhao

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

Comments Accepted to NeurIPS 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.03303 2023-05-08 cs.RO 86%

Occupancy Prediction-Guided Neural Planner for Autonomous Driving

Haochen Liu, Zhiyu Huang, Chen Lv

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2303.04218 2023-03-09 cs.LG cs.RO 86%

Deep Occupancy-Predictive Representations for Autonomous Driving

Eivind Meyer, Lars Frederik Peiss, Matthias Althoff

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

Comments Accepted at ICRA 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2112.13583 2021-12-28 cs.CV 86%

Vegetation Stratum Occupancy Prediction from Airborne LiDAR 3D Point Clouds

Ekaterina Kalinicheva, Loic Landrieu, Clément Mallet, Nesrine Chehata

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

Journal ref SilviLaser 2021 Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
1705.08781 2017-11-08 cs.RO 86%

Dynamic Occupancy Grid Prediction for Urban Autonomous Driving: A Deep Learning Approach with Fully Automatic Labeling

Stefan Hoermann, Martin Bach, Klaus Dietmayer

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

详情

展开后加载摘要…

URL PDF HTML 收藏