自动驾驶 - arXivDaily 专题

2601.14448 2026-01-22 cs.CV 83%

Gaussian Based Adaptive Multi-Modal 3D Semantic Occupancy Prediction

基于高斯的自适应多模态3D语义占位预测

A. Enes Doruk

机构 * Abdullah Enes Doruk (2025)（Abdullah Enes Doruk）

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

AI总结本文提出一种基于高斯的自适应多模态3D语义占位预测模型，通过高效3D高斯模型融合相机与激光雷达数据，提升自动驾驶安全性能。

Comments Master Thesis

2502.15438 2026-01-08 cs.CV 83%

Deflickering Vision-Based Occupancy Networks through Lightweight Spatio-Temporal Correlation

通过轻量级时空相关性提升基于视觉的占用网络

Fengcheng Yu, Haoran Xu, Canming Xia, Ziyang Zong, Guang Tan

机构 * Sun Yat-sen University（中山大学）； Peng Cheng Laboratory（鹏城实验室）

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

AI总结本文提出OccLinker框架，通过整合历史信息和双交叉注意力机制，提升基于视觉的占用网络在自动驾驶中的时间一致性与性能

2412.08243 2026-01-01 cs.CV 83%

Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction

具有解耦几何和时间建模的层次上下文对齐用于语义占用预测

Bohan Li, Jiajun Deng, Yasheng Sun, Xiaofeng Wang, Xin Jin, Wenjun Zeng

机构 * Shanghai Jiao Tong University（上海交通大学）； Eastern Institute of Technology（东部技术研究所）； Ningbo Institute of Digital Twin（宁波数字孪生研究所）； University of Adelaide（阿德莱德大学）； Tokyo Institute of Technology（东京技术大学）； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）

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

AI总结本文提出Hi-SOP方法，通过解耦几何和时间上下文进行层次化对齐，提升语义占用预测的准确性，在多个数据集上取得优异效果。

Comments IEEE TPAMI 2025

2512.19871 2025-12-24 cs.CV 83%

HyGE-Occ: Hybrid View-Transformation with 3D Gaussian and Edge Priors for 3D Panoptic Occupancy Prediction

HyGE-Occ: 基于3D高斯和边缘先验的混合视图变换用于3D全景占用预测

Jong Wook Kim, Wonseok Roh, Ha Dam Baek, Pilhyeon Lee, Jonghyun Choi, Sangpil Kim

机构 * Korea University（韩国大学）； Hyundai Motor Company（现代汽车公司）； Inha University（inha大学）

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

AI总结 HyGE-Occ通过结合3D高斯和边缘先验的混合视图变换，提升3D全景占用预测的几何一致性和边界意识，实现更精确的3D场景重建。

Comments 11 pages, 6 figures

2512.15621 2025-12-18 cs.CV 83%

OccSTeP: Benchmarking 4D Occupancy Spatio-Temporal Persistence

OccSTeP：4D占用率时空持续性基准测试

Yu Zheng, Jie Hu, Kailun Yang, Jiaming Zhang

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

AI总结 OccSTeP提出了一种4D占用率时空持续性基准，通过OccSTeP-WM模型实现对自动驾驶中未来行为的反应和前瞻性预测，实验结果显示其在语义和占用率指标上均有显著提升。

Comments 16 pages, 5 figures

2512.08506 2025-12-10 cs.CV 83%

OCCDiff: Occupancy Diffusion Model for High-Fidelity 3D Building Reconstruction from Noisy Point Clouds

OCCDiff：基于点云的高保真3D建筑重建的占用扩散模型

Jialu Sui, Rui Liu, Hongsheng Zhang

机构 * Department of Geography, Faculty of Social Science, the University of Hong Kong（地理系，社会科学学院，香港大学）

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

AI总结 OCCDiff通过潜在扩散和函数自动编码器生成高保真3D建筑重建，结合点编码器与多任务训练提升鲁棒性与精度。

2505.20951 2025-11-25 cs.CV 83%

DSOcc: Leveraging Depth Awareness and Semantic Aid to Boost Camera-Based 3D Semantic Occupancy Prediction

DSOcc: 利用深度感知和语义辅助提升基于相机的3D语义占用预测

Naiyu Fang, Zheyuan Zhou, Kang Wang, Ruibo Li, Lemiao Qiu, Shuyou Zhang, Zhe Wang, Guosheng Lin

机构 * S-Lab & College of Computing and Data Science, Nanyang Technological University（S实验室及计算与数据科学学院，南洋理工大学）； MMLab, The Chinese University of Hong Kong（M实验室，香港中文大学）； State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University（流体动力与机电系统国家重点实验室，浙江大学）； SenseTime Research, Hong Kong（商汤研究，香港）

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

AI总结 DSOcc通过深度感知和语义辅助提升基于相机的3D语义占用预测，实现高效且鲁棒的占用状态和类别推断。

2505.20641 2025-10-23 cs.CV 83%

See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction

Yuan Wu, Zhiqiang Yan, Yigong Zhang, Xiang Li, Jian Yang

机构 * PCA Lab , Nanjing University of Science and Technology（南京理工大学光电实验室）； National University of Singapore（新加坡国立大学）； Nankai University（南开大学）

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

2510.13198 2025-10-16 cs.CV 83%

Complementary Information Guided Occupancy Prediction via Multi-Level Representation Fusion

Rongtao Xu, Jinzhou Lin, Jialei Zhou, Jiahua Dong, Changwei Wang, Ruisheng Wang, Li Guo, Shibiao Xu, Xiaodan Liang

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

2510.12679 2025-10-16 cs.CV 83%

MCOP: Multi-UAV Collaborative Occupancy Prediction

Zefu Lin, Wenbo Chen, Xiaojuan Jin, Yuran Yang, Lue Fan, Yixin Zhang, Yufeng Zhang, Zhaoxiang Zhang

机构 * University of Chinese Academy of Sciences (UCAS)（中国科学院大学）； Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）； New Laboratory of Pattern Recognition (NLPR)（模式识别新实验室）； State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS)（多模态人工智能系统国家重点实验室）； Beijing University of Posts and Telecommunications (BUPT)（北京邮电大学）； Tencent（腾讯）

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

2411.07725 2025-09-11 cs.CV 83%

ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictions

Dubing Chen, Jin Fang, Wencheng Han, Xinjing Cheng, Junbo Yin, Chenzhong Xu, Fahad Shahbaz Khan, Jianbing Shen

机构 * SKL-IOTSC, CIS, University of Macau（澳门大学智能物联网与智能系统中心，计算机科学与信息学院）； CEMSE Division, King Abdullah University of Science and Technology（国王阿卜杜勒阿齐兹大学科学与技术学院）； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）； Linköping University（林雪平大学）

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

Comments ICCV 2025

2508.04705 2025-08-07 cs.CV 83%

Occupancy Learning with Spatiotemporal Memory

Ziyang Leng, Jiawei Yang, Wenlong Yi, Bolei Zhou

机构 * University of California, Los Angeles（加州大学洛杉矶分校）； University of Southern California（南加州大学）

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

Comments Accepted to ICCV2025. Project website: https://matthew-leng.github.io/stocc

2508.01704 2025-08-05 cs.CV 83%

LT-Gaussian: Long-Term Map Update Using 3D Gaussian Splatting for Autonomous Driving

Luqi Cheng, Zhangshuo Qi, Zijie Zhou, Chao Lu, Guangming Xiong

机构 * Beijing Institute of Technology（北京理工大学）

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

Comments Accepted by IV 2025

2411.16072 2025-07-31 cs.CV 83%

Language Driven Occupancy Prediction

Zhu Yu, Bowen Pang, Lizhe Liu, Runmin Zhang, Qiang Li, Si-Yuan Cao, Maochun Luo, Mingxia Chen, Sheng Yang, Hui-Liang Shen

机构 * Zhejiang University（浙江大学）； Unmanned Vehicle Dept., CaiNiao Inc., Alibaba Group（无人车辆部门，菜鸟公司，阿里巴巴集团）； Ningbo Global Innovation Center, Zhejiang University（宁波全球创新中心，浙江大学）

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

Comments ICCV 2025; Project Page: https://github.com/pkqbajng/LOcc

2507.20963 2025-07-29 cs.CV 83%

GTAD: Global Temporal Aggregation Denoising Learning for 3D Semantic Occupancy Prediction

Tianhao Li, Yang Li, Mengtian Li, Yisheng Deng, Weifeng Ge

机构 * Department of Computer and Technology, Fudan University（复旦大学计算机与技术系）； School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）； Shanghai Film Academy of Shanghai University（上海大学上海电影学院）

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

2502.05040 2025-07-08 cs.CV 83%

GaussRender: Learning 3D Occupancy with Gaussian Rendering

Loïck Chambon, Eloi Zablocki, Alexandre Boulch, Mickaël Chen, Matthieu Cord

机构 * ValeoAI ； Sorbonne University（索邦大学）

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

Comments ICCV 2025

2507.02250 2025-07-04 cs.CV 83%

FMOcc: TPV-Driven Flow Matching for 3D Occupancy Prediction with Selective State Space Model

Jiangxia Chen, Tongyuan Huang, Ke Song

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

2506.10977 2025-06-13 cs.CV 83%

QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction

Sicheng Zuo, Wenzhao Zheng, Xiaoyong Han, Longchao Yang, Yong Pan, Jiwen Lu

机构 * Tsinghua University（清华大学）； Li Auto Inc.（利亚 Auto 公司）

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

Comments Project page: https://zuosc19.github.io/QuadricFormer/

2506.09417 2025-06-13 cs.CV 83%

ODG: Occupancy Prediction Using Dual Gaussians

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

机构 * Qualcomm AI Research（高通人工智能研究）

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

2506.06128 2025-06-09 cs.CV 83%

CCLSTM: Coupled Convolutional Long-Short Term Memory Network for Occupancy Flow Forecasting

Peter Lengyel

机构 * aiMotive Budapest, Hungary（aiMotive布达佩斯，匈牙利）

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

2505.22461 2025-05-30 cs.CV 83%

SHTOcc: Effective 3D Occupancy Prediction with Sparse Head and Tail Voxels

Qiucheng Yu, Yuan Xie, Xin Tan

机构 * City University of Hong Kong（香港城市大学）； East China Normal University（东华大学）

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

2504.16346 2025-04-24 cs.RO 83%

Road Similarity-Based BEV-Satellite Image Matching for UGV Localization

Zhenping Sun, Chuang Yang, Yafeng Bu, Bokai Liu, Jun Zeng, Xiaohui Li

机构 * College of Intelligence Science and Technology, National University of Defense Technology（智能科学与技术学院，国防科技大学）

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

Comments 7 pages,9 figures,published to IROS2025

2504.01957 2025-04-04 cs.CV 83%

Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting

Shu-Wei Lu, Yi-Hsuan Tsai, Yi-Ting Chen

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

Comments Accepted to CVPR'25. https://hcis-lab.github.io/GaussianLSS/

2503.10605 2025-03-14 cs.CV 83%

OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction

Severin Heidrich, Till Beemelmanns, Alexey Nekrasov, Bastian Leibe, Lutz Eckstein

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

Comments Accepted for publication at ICRA 2025

2503.04059 2025-03-07 cs.CV 83%

H3O: Hyper-Efficient 3D Occupancy Prediction with Heterogeneous Supervision

Yunxiao Shi, Hong Cai, Amin Ansari, Fatih Porikli

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

Comments ICRA 2025

2502.20077 2025-03-03 cs.CV 83%

SegLocNet: Multimodal Localization Network for Autonomous Driving via Bird's-Eye-View Segmentation

Zijie Zhou, Zhangshuo Qi, Luqi Cheng, Guangming Xiong

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

2412.08774 2025-02-28 cs.CV 83%

ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query Decoder

Jungho Kim, Changwon Kang, Dongyoung Lee, Sehwan Choi, Jun Won Choi

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

Comments Accepted to AAAI Conference on Artificial Intelligence 2025, 15 pages, 9 figures

2502.11287 2025-02-18 cs.CV 83%

MC-BEVRO: Multi-Camera Bird Eye View Road Occupancy Detection for Traffic Monitoring

Arpitsinh Vaghela, Duo Lu, Aayush Atul Verma, Bharatesh Chakravarthi, Hua Wei, Yezhou Yang

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

2412.11210 2025-01-13 cs.CV 83%

ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction

Yi Feng, Yu Han, Xijing Zhang, Tanghui Li, Yanting Zhang, Rui Fan

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

Comments accepted to AAAI25

2403.08919 2024-11-26 cs.CV 83%

CLIP-BEVFormer: Enhancing Multi-View Image-Based BEV Detector with Ground Truth Flow

Chenbin Pan, Burhaneddin Yaman, Senem Velipasalar, Liu Ren

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

Comments CVPR 2024

Journal ref CVPR 2024

1. BEV与占用 3755 篇

Gaussian Based Adaptive Multi-Modal 3D Semantic Occupancy Prediction

Deflickering Vision-Based Occupancy Networks through Lightweight Spatio-Temporal Correlation

Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction

HyGE-Occ: Hybrid View-Transformation with 3D Gaussian and Edge Priors for 3D Panoptic Occupancy Prediction

OccSTeP: Benchmarking 4D Occupancy Spatio-Temporal Persistence

OCCDiff: Occupancy Diffusion Model for High-Fidelity 3D Building Reconstruction from Noisy Point Clouds

DSOcc: Leveraging Depth Awareness and Semantic Aid to Boost Camera-Based 3D Semantic Occupancy Prediction

See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction

Complementary Information Guided Occupancy Prediction via Multi-Level Representation Fusion

MCOP: Multi-UAV Collaborative Occupancy Prediction

ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictions

Occupancy Learning with Spatiotemporal Memory

LT-Gaussian: Long-Term Map Update Using 3D Gaussian Splatting for Autonomous Driving

Language Driven Occupancy Prediction

GTAD: Global Temporal Aggregation Denoising Learning for 3D Semantic Occupancy Prediction

GaussRender: Learning 3D Occupancy with Gaussian Rendering

FMOcc: TPV-Driven Flow Matching for 3D Occupancy Prediction with Selective State Space Model

QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction

ODG: Occupancy Prediction Using Dual Gaussians

CCLSTM: Coupled Convolutional Long-Short Term Memory Network for Occupancy Flow Forecasting

SHTOcc: Effective 3D Occupancy Prediction with Sparse Head and Tail Voxels

Road Similarity-Based BEV-Satellite Image Matching for UGV Localization

Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting

OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction

H3O: Hyper-Efficient 3D Occupancy Prediction with Heterogeneous Supervision

SegLocNet: Multimodal Localization Network for Autonomous Driving via Bird's-Eye-View Segmentation

ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query Decoder

MC-BEVRO: Multi-Camera Bird Eye View Road Occupancy Detection for Traffic Monitoring

ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction

CLIP-BEVFormer: Enhancing Multi-View Image-Based BEV Detector with Ground Truth Flow