自动驾驶 - arXivDaily 专题

2006.08383 2020-06-17 cs.CV cs.RO eess.IV 67%

Pixel Invisibility: Detecting Objects Invisible in Color Images

Yongxin Wang, Duminda Wijesekera

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

Comments 8 pages, 7 figures, submitted to NIPS 2020

1906.08469 2020-06-12 cs.RO cs.CV cs.LG eess.IV 67%

Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets

Fang-Chieh Chou, Tsung-Han Lin, Henggang Cui, Vladan Radosavljevic, Thi Nguyen, Tzu-Kuo Huang, Matthew Niedoba, Jeff Schneider, Nemanja Djuric

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

Comments Accepted for publication at IEEE Intelligent Vehicles Symposium (IV) 2020

1910.09094 2020-06-09 cs.CV cs.LG cs.RO eess.IV 67%

Self-supervised classification of dynamic obstacles using the temporal information provided by videos

Sid Ali Hamideche, Florent Chiaroni, Mohamed-Cherif Rahal

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

2003.00504 2020-03-03 cs.CV cs.AI cs.LG cs.RO 67%

MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships

Yongjian Chen, Lei Tai, Kai Sun, Mingyang Li

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

Comments CVPR 2020 accepted

2001.10773 2020-01-30 cs.CV cs.RO eess.IV 67%

Virtual KITTI 2

Yohann Cabon, Naila Murray, Martin Humenberger

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

1912.00177 2019-12-06 cs.CV cs.AI cs.LG cs.RO 67%

Urban Driving with Conditional Imitation Learning

Jeffrey Hawke, Richard Shen, Corina Gurau, Siddharth Sharma, Daniele Reda, Nikolay Nikolov, Przemyslaw Mazur, Sean Micklethwaite, Nicolas Griffiths, Amar Shah, Alex Kendall

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

Comments Under submission; added acknowledgements

1910.13955 2019-10-31 eess.IV cs.CV cs.RO 67%

LDLS: 3-D Object Segmentation Through Label Diffusion From 2-D Images

Brian H. Wang, Wei-Lun Chao, Yan Wang, Bharath Hariharan, Kilian Q. Weinberger, Mark Campbell

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

Comments Accepted for publication in IEEE Robotics and Automation Letters with presentation at IROS 2019

1909.13551 2019-10-01 cs.CV cs.RO eess.IV 67%

Enhancing Object Detection in Adverse Conditions using Thermal Imaging

Kshitij Agrawal, Anbumani Subramanian

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

Comments IROS 2019 Workshop on Towards Cognitive Vehicles

1905.01492 2019-07-18 cs.CV cs.AI cs.LG cs.RO stat.ML 67%

SoilingNet: Soiling Detection on Automotive Surround-View Cameras

Michal Uricar, Pavel Krizek, Ganesh Sistu, Senthil Yogamani

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

Comments Accepted for Oral Presentation at IEEE Intelligent Transportation Systems Conference (ITSC) 2019

1904.13010 2019-05-01 cs.IT eess.SP math.IT 67%

Realizing Multi-Point Vehicular Positioning via Millimeter-wave Transmission

Zezhong Zhang, Seung-Woo Ko, Rui Wang, Kaibin Huang

专题命中感知：autonomous driving(abstract)；LiDAR(abstract)

Comments 9 pages, 6 figures, conference version

1904.11082 2019-04-26 cs.LG stat.ML 67%

How You Act Tells a Lot: Privacy-Leakage Attack on Deep Reinforcement Learning

Xinlei Pan, Weiyao Wang, Xiaoshuai Zhang, Bo Li, Jinfeng Yi, Dawn Song

专题命中感知：autonomous driving(abstract)；LiDAR(abstract)

Comments The first three authors contributed equally. Accepted by AAMAS 2019

1707.05969 2019-01-23 physics.optics 67%

Ultrafast optical ranging using microresonator soliton frequency combs

Philipp Trocha, Denis Ganin, Maxim Karpov, Martin H. P. Pfeiffer, Arne Kordts, Jonas Krockenberger, Stefan Wolf, Pablo Marin-Palomo, Claudius Weimann, Sebastian Randel, Wolfgang Freude, Tobias J. Kippenberg, Christian Koos

专题命中感知：autonomous driving(abstract)；LiDAR(abstract)

Comments 9 pages, 3 figures, Supplementary information is attached in 'Ancillary files'

Journal ref Science 23 Feb 2018, Vol. 359, Issue 6378, pp. 887-891

1807.08894 2018-09-20 cs.RO cs.AI cs.CV cs.LG 67%

ClusterNet: 3D Instance Segmentation in RGB-D Images

Lin Shao, Ye Tian, Jeannette Bohg

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

1802.00411 2018-09-11 cs.CV cs.AI cs.LG cs.RO 67%

Dense 3D Object Reconstruction from a Single Depth View

Bo Yang, Stefano Rosa, Andrew Markham, Niki Trigoni, Hongkai Wen

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

Comments TPAMI 2018. Code and data are available at: https://github.com/Yang7879/3D-RecGAN-extended. This article extends from arXiv:1708.07969

1808.07712 2018-08-24 cs.CV cs.AI cs.RO 67%

Predicting Action Tubes

Gurkirt Singh, Suman Saha, Fabio Cuzzolin

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

Comments ECCV workshop; Anticipating Human Behaviour 2018; 16 page 7 figures

1708.07303 2018-06-18 cs.RO cs.AI cs.CV cs.LG 67%

Learning 6-DOF Grasping Interaction via Deep Geometry-aware 3D Representations

Xinchen Yan, Jasmine Hsu, Mohi Khansari, Yunfei Bai, Arkanath Pathak, Abhinav Gupta, James Davidson, Honglak Lee

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

Comments Published at ICRA 2018

1610.01238 2017-11-20 cs.RO cs.AI cs.CV cs.LG 67%

Find Your Own Way: Weakly-Supervised Segmentation of Path Proposals for Urban Autonomy

Dan Barnes, Will Maddern, Ingmar Posner

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

Comments International Conference on Robotics and Automation (ICRA), 2017. Video summary: http://youtu.be/rbZ8ck_1nZk

1703.01398 2017-10-17 cs.RO cs.AI cs.CV 67%

Sparse Depth Sensing for Resource-Constrained Robots

Fangchang Ma, Luca Carlone, Ulas Ayaz, Sertac Karaman

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

Comments 35 pages, 31 figures, 2 tables; added new results

1708.07969 2017-08-29 cs.CV cs.AI cs.LG cs.RO 67%

3D Object Reconstruction from a Single Depth View with Adversarial Learning

Bo Yang, Hongkai Wen, Sen Wang, Ronald Clark, Andrew Markham, Niki Trigoni

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

Comments ICCV Workshops 2017

1609.09365 2017-04-20 cs.CV cs.AI cs.LG cs.RO 67%

Deep Tracking on the Move: Learning to Track the World from a Moving Vehicle using Recurrent Neural Networks

Julie Dequaire, Dushyant Rao, Peter Ondruska, Dominic Wang, Ingmar Posner

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

1604.05091 2016-04-20 cs.LG cs.AI cs.CV cs.NE cs.RO 67%

End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks

Peter Ondruska, Julie Dequaire, Dominic Zeng Wang, Ingmar Posner

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

2604.03814 2026-04-07 cs.CV cs.AI 66%

InCaRPose: In-Cabin Relative Camera Pose Estimation Model and Dataset

InCaRPose：车内相对相机姿态估计模型与数据集

Felix Stillger, Lukas Hahn, Frederik Hasecke, Tobias Meisen

机构 * University of Wuppertal（伍珀塔尔大学）； Aptiv（Aptiv公司）

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

AI总结本文提出InCaRPose模型，基于Transformer架构实现车内环境下高精度相机姿态估计，通过合成数据训练实现对鱼眼镜头畸变的鲁棒性，并在7-Scenes数据集上表现优异。

Comments Accepted at the CVPR 2026 Workshop on Autonomous Driving (WAD)

2504.09195 2025-04-15 cs.CV cs.AI 66%

ReferGPT: Towards Zero-Shot Referring Multi-Object Tracking

Tzoulio Chamiti, Leandro Di Bella, Adrian Munteanu, Nikos Deligiannis

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

Comments Accepted CVPR 2025 Workshop on Distillation of Foundation Models for Autonomous Driving

2405.10577 2025-04-09 cs.CV cs.RO 66%

DuoSpaceNet: Leveraging Both Bird's-Eye-View and Perspective View Representations for 3D Object Detection

Zhe Huang, Yizhe Zhao, Hao Xiao, Chenyan Wu, Lingting Ge

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

Comments CVPR 2025 Workshop on Autonomous Driving (WAD)

2205.00613 2022-05-03 cs.CV cs.AI 66%

MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries

Tianyuan Zhang, Xuanyao Chen, Yue Wang, Yilun Wang, Hang Zhao

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

Comments Appear on CVPR 2022 Workshop on Autonomous Driving

2004.08189 2021-11-05 cs.CV cs.LG cs.RO 66%

MOPT: Multi-Object Panoptic Tracking

Juana Valeria Hurtado, Rohit Mohan, Wolfram Burgard, Abhinav Valada

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

Comments Code & models are available at http://rl.uni-freiburg.de/research/panoptictracking

Journal ref The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop on Scalability in Autonomous Driving, 2020

1904.11466 2019-04-26 cs.CV cs.LG cs.RO 66%

Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation

Gregory P. Meyer, Jake Charland, Darshan Hegde, Ankit Laddha, Carlos Vallespi-Gonzalez

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

Comments Accepted for publication at CVPR Workshop on Autonomous Driving 2019

2205.15781 2023-01-31 cs.CV 65%

Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models

Jose L. Gómez, Gabriel Villalonga, Antonio M. López

专题命中感知：autonomous driving(abstract,journal_ref)；分类 cs.CV；driving perception(journal_ref)

Comments Code available at https://github.com/JoseLGomez/Co-training_SemSeg_UDA. Paper accepted on Sensors at https://www.mdpi.com/1424-8220/23/2/621

Journal ref Sensors, Special Issue Machine Learning for Autonomous Driving Perception and Prediction (2023)

2608.18715 2026-08-20 cs.CV cs.AI cs.LG 新提交 62%

The Impact of CutMix on Reliability and Robustness in Semantic Segmentation

CutMix对语义分割中可靠性与鲁棒性的影响

Steven Landgraf, Markus Ulrich

机构 * Institute of Photogrammetry and Remote Sensing (IPF), Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院摄影测量与遥感研究所）

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

AI总结该研究探究CutMix对语义分割的影响，发现其对分割准确率影响微小，但可提升模型可靠性，尤其在分布偏移场景下，增强的是校准度与不确定性可信度，对安全关键应用意义重大。

Comments Accepted for publication in the ISPRS Annals (ISPRS Congress 2026, Toronto, Oral Presentation)

2608.14603 2026-08-19 cs.NI cs.AI cs.CV cs.IT math.IT 版本更新 62%

HMS-SCP: Task-Oriented Multi-Scale Semantic Communication for V2X Cooperative Perception

通过语义感知协同感知扩展智能交通系统的安全 horizon

Chun-Yeow Yeoh, Chee Keong Tan, Joanne Mun-Yee Lim, Heng-Siong Lim

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

AI总结本文提出 HMS-SCP 框架，通过多尺度语义冗余与 JSCC 编码实现带宽效率与鲁棒性的平衡，在 V2X 环境中保障安全关键型协同感知的性能。

Comments 15 pages, 7 figures, 6 tables, Submitted to IEEE Transactions on Vehicular Technology (TVT)

1. 感知 6063 篇

Pixel Invisibility: Detecting Objects Invisible in Color Images

Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets

Self-supervised classification of dynamic obstacles using the temporal information provided by videos

MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships

Virtual KITTI 2

Urban Driving with Conditional Imitation Learning

LDLS: 3-D Object Segmentation Through Label Diffusion From 2-D Images

Enhancing Object Detection in Adverse Conditions using Thermal Imaging

SoilingNet: Soiling Detection on Automotive Surround-View Cameras

Realizing Multi-Point Vehicular Positioning via Millimeter-wave Transmission

How You Act Tells a Lot: Privacy-Leakage Attack on Deep Reinforcement Learning

Ultrafast optical ranging using microresonator soliton frequency combs

ClusterNet: 3D Instance Segmentation in RGB-D Images

Dense 3D Object Reconstruction from a Single Depth View

Predicting Action Tubes

Learning 6-DOF Grasping Interaction via Deep Geometry-aware 3D Representations

Find Your Own Way: Weakly-Supervised Segmentation of Path Proposals for Urban Autonomy

Sparse Depth Sensing for Resource-Constrained Robots

3D Object Reconstruction from a Single Depth View with Adversarial Learning

Deep Tracking on the Move: Learning to Track the World from a Moving Vehicle using Recurrent Neural Networks

End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks

InCaRPose: In-Cabin Relative Camera Pose Estimation Model and Dataset

ReferGPT: Towards Zero-Shot Referring Multi-Object Tracking

DuoSpaceNet: Leveraging Both Bird's-Eye-View and Perspective View Representations for 3D Object Detection

MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries

MOPT: Multi-Object Panoptic Tracking

Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation

Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models

The Impact of CutMix on Reliability and Robustness in Semantic Segmentation

HMS-SCP: Task-Oriented Multi-Scale Semantic Communication for V2X Cooperative Perception