自动驾驶

Open-set Anomaly Segmentation in Complex Scenarios

Song Xia, Yi Yu, Henghui Ding, Wenhan Yang, Shifei Liu, Alex C. Kot, Xudong Jiang

机构 * Rapid-Rich Object Search Lab, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore（快速丰富目标搜索实验室，电气与电子工程学院，南洋理工大学，新加坡） ； Rapid-Rich Object Search Lab, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore（快速丰富目标搜索实验室，跨学科研究生项目，南洋理工大学，新加坡） ； Pengcheng Laboratory, Shenzhen, China（鹏城实验室，深圳，中国） ； Institute of Big Data, Fudan University, Shanghai, China（大数据研究院，复旦大学，上海，中国） 纠错

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

A Data-Centric Approach to 3D Semantic Segmentation of Railway Scenes

Nicolas Münger, Max Peter Ronecker, Xavier Diaz, Michael Karner, Daniel Watzenig, Jan Skaloud

机构 * SETLabs Research GmbH（SETLabs研究公司） ； Graz University of Technology（格拉茨技术大学） ； EPFL - Swiss Federal Technology Institute of Lausanne（洛桑联邦理工学院） 纠错

专题命中 感知 ：LiDAR(abstract)；分类 cs.CV

Comments Accepted at the 28th Computer Vision Winter Workshop 2025

What is the Added Value of UDA in the VFM Era?

Brunó B. Englert, Tommie Kerssies, Gijs Dubbelman

机构 * Eindhoven University of Technology（埃因霍温理工大学） 纠错

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

M2P2: A Multi-Modal Passive Perception Dataset for Off-Road Mobility in Extreme Low-Light Conditions

Aniket Datar, Anuj Pokhrel, Mohammad Nazeri, Madhan B. Rao, Chenhui Pan, Yufan Zhang, Andre Harrison, Maggie Wigness, Philip R. Osteen, Jinwei Ye, Xuesu Xiao

机构 * George Mason University（乔治·马歇尔大学） 纠错

专题命中 感知 ：LiDAR(abstract)；分类 cs.RO

SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems

Manjunath D, Aniruddh Sikdar, Prajwal Gurunath, Sumanth Udupa, Suresh Sundaram

机构 * Department of Aerospace Engineering, Indian Institute of Science（航空航天工程系，印度科学研究院） ； Robert Bosch Centre for Cyber Physical Systems, Indian Institute of Science（网络物理系统研究中心，印度科学研究院） 纠错

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

Comments Accepted at CVPR-W PBVS 2025

SMTT: Novel Structured Multi-task Tracking with Graph-Regularized Sparse Representation for Robust Thermal Infrared Target Tracking

Shang Zhang, HuiPan Guan, XiaoBo Ding, Ruoyan Xiong, Yue Zhang

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

S-EO: A Large-Scale Dataset for Geometry-Aware Shadow Detection in Remote Sensing Applications

Elías Masquil, Roger Marí, Thibaud Ehret, Enric Meinhardt-Llopis, Pablo Musé, Gabriele Facciolo

机构 * IIE, Facultad de Ingeniería, Universidad de la República（拉普拉塔大学工程学院） ； Digital Sense（数字感知） ； Eurecat, Centre Tecnològic de Catalunya（加泰罗尼亚技术中心） ； Multimedia Technologies（多媒体技术） ； AMIAD, Pôle Recherche（AMIAD研究机构） ； Université Paris-Saclay, ENS Paris-Saclay, CNRS, Centre Borelli（巴黎-萨克雷大学、巴黎-萨克雷高等师范学院、国家科学研究中心、Borelli中心） 纠错

专题命中 感知 ：LiDAR(abstract)；分类 cs.CV

Comments Accepted at Earthvision 2025 (CVPR Workshop)

TSceneJAL: Joint Active Learning of Traffic Scenes for 3D Object Detection

Chenyang Lei, Weiyuan Peng, Guang Zhou, Meiying Zhang, Qi Hao, Chunlin Ji, Chengzhong Xu

机构 * Research Institute of Trustworthy Autonomous Systems, and Department of Computer Science and Engineering, Southern University of Science and Technology (SUSTech), China（可信自主系统研究 institute，计算机科学与工程系，南方科技大学，中国） ； State Key Lab of Internet of Things for Smart City, University of Macau, China（智慧城市物联网国家重点实验室，澳门大学，中国） ； Kuang-Chi Institute of Advanced Technology, China（广驰先进技术研究所，中国） ； Shenzhen Deeproute.ai Co.,Ltd, China（深圳DeepRoute.ai有限公司，中国） 纠错

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

Exploring Modality Guidance to Enhance VFM-based Feature Fusion for UDA in 3D Semantic Segmentation

Johannes Spoecklberger, Wei Lin, Pedro Hermosilla, Sivan Doveh, Horst Possegger, M. Jehanzeb Mirza

机构 * Institute of Visual Computing, Graz University of Technology（视觉计算研究所，格拉茨技术大学） ； JKU LINZ（JKU林茨） ； TU Wien（维也纳技术大学） ； IBM Research（IBM研究院） ； MIT CSAIL（麻省理工学院计算机科学与人工智能实验室） 纠错

专题命中 感知 ：LiDAR(abstract)；分类 cs.CV

Lightweight Road Environment Segmentation using Vector Quantization

Jiyong Kwag, Alper Yilmaz, Charles Toth

机构 * Dept. of Civil Engineering, The Ohio State University（土木工程系，俄亥俄州立大学） 纠错

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

Journal ref ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci. 2025 (Best Paper Award)

Weak Cube R-CNN: Weakly Supervised 3D Detection using only 2D Bounding Boxes

Andreas Lau Hansen, Lukas Wanzeck, Dim P. Papadopoulos

机构 * Technical University of Denmark（丹麦技术大学） ； Pioneer Center for AI（先锋人工智能中心） 纠错

专题命中 感知 ：LiDAR(abstract)；分类 cs.CV

Comments 14 pages, 5 figures. Accepted for 23rd Scandinavian Conference, SCIA 2025, Reykjavik, Iceland

Perceive With Confidence: Statistical Safety Assurances for Navigation with Learning-Based Perception

Zhiting Mei, Anushri Dixit, Meghan Booker, Emily Zhou, Mariko Storey-Matsutani, Allen Z. Ren, Ola Shorinwa, Anirudha Majumdar

专题命中 感知 ：occupancy(abstract)；分类 cs.RO

Comments Videos and code can be found at https://perceive-with-confidence.github.io

GroundSLAM: A Robust Visual SLAM System for Warehouse Robots Using Ground Textures

Kuan Xu, Zheng Yang, Lihua Xie, Chen Wang

专题命中 感知 ：LiDAR(abstract)；分类 cs.RO

FreeDOM: Online Dynamic Object Removal Framework for Static Map Construction Based on Conservative Free Space Estimation

Chen Li, Wanlei Li, Wenhao Liu, Yixiang Shu, Yunjiang Lou

专题命中 感知 ：LiDAR(abstract)；分类 cs.RO

InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception

Haijie Li, Yanmin Wu, Jiarui Meng, Qiankun Gao, Zhiyao Zhang, Ronggang Wang, Jian Zhang

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

Comments 14 pages, accepted by CVPR 2025 as poster

A Visual-Inertial Motion Prior SLAM for Dynamic Environments

Weilong Sun, Yumin Zhang, Boren Wei

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

X2BR: High-Fidelity 3D Bone Reconstruction from a Planar X-Ray Image with Hybrid Neural Implicit Methods

Gokce Guven, H. Fatih Ugurdag, Hasan F. Ates

专题命中 感知 ：occupancy(abstract)；分类 cs.CV

TinyCenterSpeed: Efficient Center-Based Object Detection for Autonomous Racing

Neil Reichlin, Nicolas Baumann, Edoardo Ghignone, Michele Magno

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

Road Grip Uncertainty Estimation Through Surface State Segmentation

Jyri Maanpää, Julius Pesonen, Iaroslav Melekhov, Heikki Hyyti, Juha Hyyppä

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

Comments 15 pages, 5 figures (supplementary material 2 pages, 1 figure). Anonymized version submitted to Scandinavian Conference on Image Analysis (SCIA) 2025

Enhanced Cooperative Perception Through Asynchronous Vehicle to Infrastructure Framework with Delay Mitigation for Connected and Automated Vehicles

Nithish Kumar Saravanan, Varun Jammula, Yezhou Yang, Jeffrey Wishart, Junfeng Zhao

专题命中 感知 ：LiDAR(abstract)；分类 cs.RO

Comments 9 pages, 9 figures, This paper is under review of SAE Journal of Connected and Automated Vehicles

Enhancing Lane Segment Perception and Topology Reasoning with Crowdsourcing Trajectory Priors

Peijin Jia, Ziang Luo, Tuopu Wen, Mengmeng Yang, Kun Jiang, Le Cui, Diange Yang

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

Comments 8 pages

OoDIS: Anomaly Instance Segmentation and Detection Benchmark

Alexey Nekrasov, Rui Zhou, Miriam Ackermann, Alexander Hermans, Bastian Leibe, Matthias Rottmann

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

Comments Accepted for publication at ICRA 2025. Project page: https://vision.rwth-aachen.de/oodis

MovSAM: A Single-image Moving Object Segmentation Framework Based on Deep Thinking

Chang Nie, Yiqing Xu, Guangming Wang, Zhe Liu, Yanzi Miao, Hesheng Wang

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

Learning Occlusion-aware Decision-making from Agent Interaction via Active Perception

Jie Jia, Yiming Shu, Zhongxue Gan, Wenchao Ding

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

Comments Accepted by IEEE Intelligent Vehicles Symposium (IV)

Texture2LoD3: Enabling LoD3 Building Reconstruction With Panoramic Images

Wenzhao Tang, Weihang Li, Xiucheng Liang, Olaf Wysocki, Filip Biljecki, Christoph Holst, Boris Jutzi

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

Comments Accepted for CVPRW '25

EMF: Event Meta Formers for Event-based Real-time Traffic Object Detection

Muhammad Ahmed Ullah Khan, Abdul Hannan Khan, Andreas Dengel

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

Comments 10 pages, 2 figures

Adaptive Neural Networks for Intelligent Data-Driven Development

Youssef Shoeb, Azarm Nowzad, Hanno Gottschalk

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

Comments Accepted to 2025 IEEE Intelligent Vehicles Symposium (IV)

Exploring Semi-Supervised Learning for Online Mapping

Adam Lilja, Erik Wallin, Junsheng Fu, Lars Hammarstrand

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

Attention-Aware Multi-View Pedestrian Tracking

Reef Alturki, Adrian Hilton, Jean-Yves Guillemaut

专题命中 感知 ：BEV(abstract)；分类 cs.CV

Enhancing Traffic Sign Recognition On The Performance Based On Yolov8

Baba Ibrahim, Zhou Kui

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

Comments 27 Pages, 6 Figures, 10 Tables and 20 References