自动驾驶

aUToTrack: A Lightweight Object Detection and Tracking System for the SAE AutoDrive Challenge

Keenan Burnett, Sepehr Samavi, Steven L. Waslander, Timothy D. Barfoot, Angela P. Schoellig

专题命中 感知 ：self-driving(abstract)；LiDAR(abstract)；分类 cs.RO

Comments Accepted to CRV (Computer and Robot Vision) 2019

Multimodal 3D Object Detection from Simulated Pretraining

Åsmund Brekke, Fredrik Vatsendvik, Frank Lindseth

专题命中 感知 ：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.CV

Comments 12 pages, part of proceedings for the NAIS 2019 symposium

Cooper: Cooperative Perception for Connected Autonomous Vehicles based on 3D Point Clouds

Qi Chen, Sihai Tang, Qing Yang, Song Fu

专题命中 感知 ：self-driving(abstract)；LiDAR(abstract)；分类 cs.CV

Comments Accepted by the 39th IEEE International Conference on Distributed Computing Systems (ICDCS 2019)

PointPillars: Fast Encoders for Object Detection from Point Clouds

Alex H. Lang, Sourabh Vora, Holger Caesar, Lubing Zhou, Jiong Yang, Oscar Beijbom

专题命中 感知 ：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.CV

Comments 9 pages. v1 is initial submission to CVPR 2019. v2 is final version accepted for publication at CVPR 2019

Deep Multi-Sensor Lane Detection

Min Bai, Gellert Mattyus, Namdar Homayounfar, Shenlong Wang, Shrinidhi Kowshika Lakshmikanth, Raquel Urtasun

专题命中 感知 ：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.CV

Comments IEEE International Conference on Intelligent Robots and Systems (IROS) 2018

PIXOR: Real-time 3D Object Detection from Point Clouds

Bin Yang, Wenjie Luo, Raquel Urtasun

专题命中 感知 ：autonomous driving(abstract)；BEV(abstract)；分类 cs.CV

Comments Update of CVPR2018 paper: correct timing, fix typos, add acknowledgement

End to End Video Segmentation for Driving : Lane Detection For Autonomous Car

Wenhui Zhang, Tejas Mahale

专题命中 感知 ：autonomous driving(abstract)；self-driving(abstract)；分类 cs.CV

Comments arXiv admin note: text overlap with arXiv:1806.07226 by other authors

A Joint 3D-2D based Method for Free Space Detection on Roads

Suvam Patra, Pranjal Maheshwari, Shashank Yadav, Chetan Arora, Subhashis Banerjee

专题命中 感知 ：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.CV

Comments Accepted for publication at IEEE WACV 2018

Complex-YOLO: Real-time 3D Object Detection on Point Clouds

Martin Simon, Stefan Milz, Karl Amende, Horst-Michael Gross

专题命中 感知 ：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.CV

Combined Image- and World-Space Tracking in Traffic Scenes

Aljosa Osep, Wolfgang Mehner, Markus Mathias, Bastian Leibe

专题命中 感知 ：self-driving(abstract)；LiDAR(abstract)；分类 cs.CV

Comments 8 pages, 7 figures, 2 tables. ICRA 2017 paper

Deconvolutional Networks for Point-Cloud Vehicle Detection and Tracking in Driving Scenarios

Victor Vaquero, Ivan del Pino, Francesc Moreno-Noguer, Joan Solà, Alberto Sanfeliu, Juan Andrade-Cetto

专题命中 感知 ：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.CV

Comments Presented in IEEE ECMR 2017. IEEE Copyrights: Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

Leveraging Pre-Trained 3D Object Detection Models For Fast Ground Truth Generation

Jungwook Lee, Sean Walsh, Ali Harakeh, Steven L. Waslander

专题命中 感知 ：autonomous driving(abstract)；self-driving(abstract)；分类 cs.AI

Joint 3D Proposal Generation and Object Detection from View Aggregation

Jason Ku, Melissa Mozifian, Jungwook Lee, Ali Harakeh, Steven Waslander

专题命中 感知 ：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.CV

Comments For any inquiries contact aharakeh(at)uwaterloo(dot)ca

Accurate Deep Direct Geo-Localization from Ground Imagery and Phone-Grade GPS

Shaohui Sun, Ramesh Sarukkai, Jack Kwok, Vinay Shet

专题命中 感知 ：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.CV

Comments To appear in CVPR 2018 Workshops

Fast, Accurate Thin-Structure Obstacle Detection for Autonomous Mobile Robots

Chen Zhou, Jiaolong Yang, Chunshui Zhao, Gang Hua

专题命中 感知 ：self-driving(abstract)；LiDAR(abstract)；分类 cs.CV

Comments Appeared at IEEE CVPR 2017 Workshop on Embedded Vision

3D Object Proposals using Stereo Imagery for Accurate Object Class Detection

Xiaozhi Chen, Kaustav Kundu, Yukun Zhu, Huimin Ma, Sanja Fidler, Raquel Urtasun

专题命中 感知 ：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.CV

Comments 14 pages, 12 figures

Non-line-of-sight tracking of people at long range

Susan Chan, Ryan E. Warburton, Genevieve Gariepy, Jonathan Leach, Daniele Faccio

专题命中 感知 ：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.CV

Road Detection through Supervised Classification

Yasamin Alkhorshid, Kamelia Aryafar, Sven Bauer, Gerd Wanielik

专题命中 感知 ：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.CV

AutoVDC: Automated Vision Data Cleaning Using Vision-Language Models

AutoVDC：利用视觉-语言模型实现自动化视觉数据清洗

Santosh Vasa, Aditi Ramadwar, Jnana Rama Krishna Darabattula, Md Zafar Anwar, Stanislaw Antol, Andrei Vatavu, Thomas Monninger, Sihao Ding

机构 * Mercedes-Benz Research & Development North America（梅赛德斯-奔驰北美研发公司） ； University of Stuttgart, Institute for Artificial Intelligence（斯图加特大学人工智能研究所） 纠错

专题命中 感知 ：autonomous driving(abstract,comments)；分类 cs.RO、cs.CV、cs.AI

AI总结 本文提出AutoVDC框架，利用视觉-语言模型自动识别视觉数据集中的错误标注，提升数据质量。通过KITTI和nuImages数据集验证，展示了方法在错误检测和数据清洗中的高性能。

Comments Accepted to IV 2026 Drive-X Foundation Models for Autonomous Driving (Oral presentation)

Vehicle Re-ID for Surround-view Camera System

Zizhang Wu, Man Wang, Lingxiao Yin, Weiwei Sun, Jason Wang, Huangbin Wu

专题命中 感知 ：autonomous driving(abstract,comments)；分类 cs.RO、cs.CV、eess.IV

Comments CVPR 2020 workshop on Scalability in Autonomous Driving

Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in Crowded Traffic Scenes

Nils Gählert, Niklas Hanselmann, Uwe Franke, Joachim Denzler

专题命中 感知 ：autonomous driving(abstract,comments)；分类 cs.RO、cs.CV、eess.IV

Comments Machine Learning for Autonomous Driving Workshop at the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada

Open-World Hierarchical Perception: Taxonomic Abstraction over Class-Agnostic Proposals for the Safe Handling of Out-of-Vocabulary Road Objects

开放世界层次感知：针对类无关候选区域的分类抽象，用于安全处理词汇外道路对象

Felix Schaller

专题命中 感知 ：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

AI总结 本文提出开放世界层次感知层，在类无关区域候选上实现分类抽象，通过结合三类开放世界信号，在自动驾驶留类基准测试中，可安全处理词汇外道路对象且无分类错误。

Comments 6 pages, 4 figures, 1 table. Third paper in a series; v1 archived at Zenodo, doi:10.5281/zenodo.21593472. Code: https://github.com/freshNfunky/IE2025-Research-Paper

Sovereign Cognitive Digital Twins: Fusing 6G ISAC, AI-RAN, and Zero-Trust Edge Grids for National Resilience in the Global South

主权认知数字孪生：融合6G感知通信一体化（ISAC）、AI-RAN与零信任边缘网格，服务全球南方国家的韧性建设

Zoe Aiyanna M. Cayetano, George M. Gichuru, Taijuo T. Morris

专题命中 感知 ：LiDAR(abstract,abstract_cn)

AI总结 针对小岛屿发展中国家灾害感知不足问题，本文提出融合6G ISAC、AI-RAN与零信任边缘网格的主权认知数字孪生架构，通过射线追踪模拟验证信道特性，以巴巴多斯为参考案例服务国家韧性建设。

Comments 16 pages, 14 figures, 7 tables. Code and reproduction instructions available; see the Code Availability section. Code: https://doi.org/10.5281/zenodo.21708211 (v1.0-paper2)

3DPipe: A Pipelined GPU Framework for Scalable Generalized Spatial Join over Polyhedral Objects

3DPipe：一种用于可扩展多面体对象通用空间连接的流水线GPU框架

Lyuheng Yuan, Da Yan, Saugat Adhikari, Akhlaque Ahmad, Fusheng Wang

专题命中 感知 ：LiDAR(abstract,abstract_cn)

AI总结 本文提出3DPipe，一种利用GPU并行性处理多面体对象空间连接的流水线框架，通过多级剪枝策略和分块流式处理提升效率，实验显示其比现有最佳GPU方案TDBase快9倍。

See Silhouettes in Motion with Neuromorphic Vision

用神经形态视觉感知运动中的轮廓

Pei Zhang, Shijie Lin, Zhou Ge, Jinpeng Chen, Wei Pu

机构 * School of Electrical Engineering, Guangxi University（广西大学电气工程学院） ； Department of Computer Science, The University of Hong Kong（香港大学计算机科学系） ； School of Mechatronic Engineering and Automation, Shanghai University（上海大学机电工程与自动化学院） ； SHU General Intelligent Robotics Research Institute（SHU通用智能机器人研究院） ； School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications（北京邮电大学计算机科学学院（国家试点软件学院）） ； School of Information and Communication Engineering, University of Electronic Science and Technology of China（电子科技大学信息与通信工程学院） 纠错

专题命中 感知 ：self-driving(abstract)；分类 cs.RO、cs.CV、eess.IV

AI总结 本文提出了一种双模方法，利用帧和事件的协同作用，在仅CPU的设备上实现实时高帧率二值化，有效减少运动模糊并提升在恶劣光照下的性能，为资源受限边缘平台的轻量感知和交互铺平道路。

Comments 13 pages, 15 figures, and 5 tables. This work is under review. Project page: https://github.com/pz-even/event_binarization

Seeing Roads Through Words: A Language-Guided Framework for RGB-T Driving Scene Segmentation

通过文字看道路：一种语言引导的RGB-T驾驶场景分割框架

Ruturaj Reddy, Hrishav Bakul Barua, Junn Yong Loo, Thanh Thi Nguyen, Ganesh Krishnasamy

机构 * National University of Singapore（新加坡国立大学） ； University of Technology Sydney（悉尼科技大学） 纠错

专题命中 感知 ：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

AI总结 提出CLARITY框架，利用视觉语言模型先验动态调整RGB-T融合策略，并引入暗目标语义保留和层次化解码器，在MFNet数据集上达到62.3% mIoU和77.5% mAcc的新SOTA。

Learned Non-Maximum Suppression for 3D Object Detection

用于3D目标检测的学习型非极大值抑制

Timo Osterburg, Stefan Schütte, Torsten Bertram

机构 * Institute of Control Theory and Systems Engineering, TU Dortmund University（控制理论与系统工程研究所，多特蒙德技术大学） 纠错

专题命中 感知 ：LiDAR(abstract)；分类 cs.RO、cs.CV、cs.AI

AI总结 提出两种基于学习的过滤模块（D2D-Rescore和GossipNet3D）替代启发式NMS，通过检测间关系提升3D检测性能，尤其改善小物体和稀有类别的检测精度。

Comments 6 pages, accepted at IEEE Intelligent Vehicles Symposium (IV) 2026

FusionSense: Tri-Stage Near-Sensor Learning for Runtime-Adaptive Multimodal Edge Intelligence

FusionSense: 用于运行时自适应多模态边缘智能的三阶段近传感器学习

Sanggeon Yun, Ryozo Masukawa, Minhyoung Na, Hyunwoo Oh, Yoshiki Yamaguchi, Wenjun Huang, SungHeon Jeong, Mohsen Imani

机构 * University of California, Irvine（加州大学尔湾分校） ； Kookmin University（韩国国民大学） ； Shibaura Institute of Technology（武藏技术大学） 纠错

专题命中 感知 ：LiDAR(abstract,abstract_cn)

AI总结 提出FusionSense框架，通过三阶段训练（服务器端融合模型学习、过滤安全标签量化模态必要性、边缘融合模型压缩）实现近传感器分类器，在保持任务质量的同时大幅降低能耗和数据传输。

Comments Accepted to ISLPED 2026

Can VLMs Unlock Semantic Anomaly Detection? A Framework for Structured Reasoning

VLMs能否解锁语义异常检测？一个结构化推理的框架

Roberto Brusnicki, David Pop, Yuan Gao, Mattia Piccinini, Johannes Betz

机构 * Professorship of Autonomous Vehicle Systems TUM School of Engineering ； Design, Technical University of Munich Munich, Germany 纠错

专题命中 感知 ：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

AI总结 本文提出SAVANT框架，通过结构化推理方法提升VLM在语义异常检测中的性能，实现对自动驾驶场景中罕见异常情况的更准确识别。

Comments 8 pages, 5 figures

Intensity-guided pose-free multiview fusion for single photon sensing

基于强度的无姿态多视角融合单光子传感

Jinyi Liu, Lijun Liu, Shuming Cheng, Xiaomin Hu, Yiguang Hong, Weiping Zhang

专题命中 感知 ：LiDAR(abstract,abstract_cn)

AI总结 本文提出一种无姿态多视角融合框架，通过结合物理感知预处理、几何-强度网格特征聚合、全局匹配和局部歧义消除，实现单光子传感的多视角配准，提升了在极端环境下的点云重建一致性。