3D 视觉

SegVec3D: A Method for Vector Embedding of 3D Objects Oriented Towards Robot manipulation

Zhihan Kang, Boyu Wang

机构 * Northwestern Polytechnical University（西北工业大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Undergraduate Theis; 12 pages, 6 figures

StixelNExT++: Lightweight Monocular Scene Segmentation and Representation for Collective Perception

Marcel Vosshans, Omar Ait-Aider, Youcef Mezouar, Markus Enzweiler

机构 * Institut Pascal ISPR (Image, Systems of Perception, Robotics), Universite Clermont Auvergne INP / CNRS（帕斯卡尔研究所（图像、感知系统、机器人），克莱蒙特大学INP/CNRS） ； Institute for Intelligent Systems at Esslingen University of Applied Sciences（埃斯林根应用科学大学智能系统研究所） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Label-Efficient LiDAR Panoptic Segmentation

Ahmet Selim Çanakçı, Niclas Vödisch, Kürsat Petek, Wolfram Burgard, Abhinav Valada

机构 * Department of Computer Science, University of Freiburg（弗赖堡大学计算机科学系） ； Department of Eng., University of Technology Nuremberg（纽伦堡技术大学工程系） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted for the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025

VISC: mmWave Radar Scene Flow Estimation using Pervasive Visual-Inertial Supervision

Kezhong Liu, Yiwen Zhou, Mozi Chen, Jianhua He, Jingao Xu, Zheng Yang, Chris Xiaoxuan Lu, Shengkai Zhang

机构 * State Key Laboratory of Maritime Technology and Safety（maritime技术与安全国家重点实验室） ； Wuhan University of Technology（武汉理工大学） ； University of Essex（埃塞克斯大学） ； Carnegie Mellon University（卡内基梅隆大学） ； Tsinghua University（清华大学） ； University College London（伦敦大学学院） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Epipolar Attention Field Transformers for Bird's Eye View Semantic Segmentation

Christian Witte, Jens Behley, Cyrill Stachniss, Marvin Raaijmakers

机构 * CARIAD SE ； Center for Robotics, University of Bonn（机器人中心，波恩大学） ； Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔人工智能与机器学习研究所） 纠错

专题命中 点云 ：spatial understanding(abstract)；分类 cs.CV、cs.RO

Comments Accepted at WACV 2025

Anyview: Generalizable Indoor 3D Object Detection with Variable Frames

Zhenyu Wu, Xiuwei Xu, Ziwei Wang, Chong Xia, Linqing Zhao, Jiwen Lu, Haibin Yan

机构 * School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications（智能工程与自动化学院，北京邮电大学） ； Department of Automation, Tsinghua University（自动化系，清华大学） ； School of Electrical and Electronic Engineering, Nanyang Technological University（电子与电气工程学院，南洋理工大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 11 pages, 7 figures

Rethink 3D Object Detection from Physical World

Satoshi Tanaka, Koji Minoda, Fumiya Watanabe, Takamasa Horibe

机构 * TIER IV, Inc（Tier IV公司） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 15 pages, 10 figures

Multimodal Object Detection using Depth and Image Data for Manufacturing Parts

Nazanin Mahjourian, Vinh Nguyen

机构 * Department of Mechanical Engineering - Engineering Mechanics, Michigan Technological University（机械工程系-工程力学系，密歇根技术大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

SAM4D: Segment Anything in Camera and LiDAR Streams

Jianyun Xu, Song Wang, Ziqian Ni, Chunyong Hu, Sheng Yang, Jianke Zhu, Qiang Li

机构 * Unmanned Vehicle Dept., CaiNiao Inc., Alibaba Group（阿里巴巴集团 Cainiao 部门） ； Zhejiang University（浙江大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted by ICCV2025, Project Page: https://SAM4D-Project.github.io

BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images

Lun Luo, Shuhang Zheng, Yixuan Li, Yongzhi Fan, Beinan Yu, Siyuan Cao, Huiliang Shen

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted by ICCV 2023

Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation

Junjie Chen, Yuecong Xu, Haosheng Li, Kemi Ding

机构 * School of Automation and Intelligent Manufacturing (AIM), Southern University of Science and Technology, Shenzhen, China（自动化与智能制造学院（AIM），南方科技大学，深圳，中国） ； Department of Electrical and Computer Engineering, National University of Singapore（电气与计算机工程系，新加坡国立大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments This paper has been accepted to the 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)

FusionForce: End-to-end Differentiable Neural-Symbolic Layer for Trajectory Prediction

Ruslan Agishev, Karel Zimmermann

机构 * Faculty of Electrical Engineering, Czech Technical University in Prague（捷克技术大学布拉格电子工程学院） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Code: https://github.com/ctu-vras/fusionforce

CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMs

Siyu Wang, Cailian Chen, Xinyi Le, Qimin Xu, Lei Xu, Yanzhou Zhang, Jie Yang

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.GR

Comments Accepted at AAAI 2025 (Vol. 39, No. 8), pages 7880-7888. DOI: 10.1609/aaai.v39i8.32849

Journal ref Proc. of the AAAI Conf. on Artificial Intelligence, 39(8):7880-7888, 2025

A workflow for generating synthetic LiDAR datasets in simulation environments

Abhishek Phadke, Shakib Mahmud Dipto, Pratip Rana

机构 * School of Engineering \& Computing Christopher Newport University ； Department of Computer Science Old Dominion University 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Multi-GraspLLM: A Multimodal LLM for Multi-Hand Semantic Guided Grasp Generation

Haosheng Li, Weixin Mao, Weipeng Deng, Chenyu Meng, Haoqiang Fan, Tiancai Wang, Yoshie Osamu, Ping Tan, Hongan Wang, Xiaoming Deng

机构 * Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所） ； Waseda University（早稻田大学） ； University of Hong Kong（香港大学） ； MEGVII Technology（美格智能科技） ； Hong Kong University of Science and Technology（香港科技大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 16 pages, 10 figures

CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image

Jingshun Huang, Haitao Lin, Tianyu Wang, Yanwei Fu, Xiangyang Xue, Yi Zhu

机构 * Fudan University（复旦大学） ； Huawei, Noah’s Ark Lab（华为诺亚实验室） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments To appear in CVPR 2025 (Highlight)

LiDAR Based Semantic Perception for Forklifts in Outdoor Environments

Benjamin Serfling, Hannes Reichert, Lorenzo Bayerlein, Konrad Doll, Kati Radkhah-Lens

机构 * Faculty of Engineering and Informatics, University of Applied Sciences Aschaffenburg（应用科学阿施芬堡大学工程与信息学院） ； Linde Material Handling GmbH, Kion Group（林德物料搬运有限公司，Kion集团） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

MVTN: Learning Multi-View Transformations for 3D Understanding

Abdullah Hamdi, Faisal AlZahrani, Silvio Giancola, Bernard Ghanem

机构 * King Abdullah University of Science and Technology (KAUST)（卡斯特国王大学（KAUST）） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.GR

Comments under review journal extension for the ICCV 2021 paper arXiv:2011.13244

RE-TRIP : Reflectivity Instance Augmented Triangle Descriptor for 3D Place Recognition

Yechan Park, Gyuhyeon Pak, Euntai Kim

机构 * Department of Vehicle Convergence Engineering, Yonsei University（yonsei大学车辆融合工程系） ； Department of Electrical and Electronic Engineering, Yonsei University（yonsei大学电气电子工程系） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

GOTPR: General Outdoor Text-based Place Recognition Using Scene Graph Retrieval with OpenStreetMap

Donghwi Jung, Keonwoo Kim, Seong-Woo Kim

机构 * Seoul National University（首尔国立大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Journal ref IEEE Robotics and Automation Letters, vol. 10, no. 6, pp. 6488-6495, June 2025

4D-ROLLS: 4D Radar Occupancy Learning via LiDAR Supervision

Ruihan Liu, Xiaoyi Wu, Xijun Chen, Liang Hu, Yunjiang Lou

机构 * Department of Automation, School of Intelligence Science and Engineering, Harbin Institute of Technology（自动化系、智能科学与工程学院、哈尔滨工业大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

RS2AD: End-to-End Autonomous Driving Data Generation from Roadside Sensor Observations

Ruidan Xing, Runyi Huang, Qing Xu, Lei He

机构 * School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动系统学院） ； State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University（清华大学智能绿色车辆与移动系统国家重点实验室） ； School of Instrumentation and Optoelectronic Engineering, BeiHang University（北航仪器与光电工程学院） ； Department of Automation, Tsinghua University（清华大学自动化系） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos

Prithviraj Banerjee, Sindi Shkodrani, Pierre Moulon, Shreyas Hampali, Shangchen Han, Fan Zhang, Linguang Zhang, Jade Fountain, Edward Miller, Selen Basol, Richard Newcombe, Robert Wang, Jakob Julian Engel, Tomas Hodan

机构 * Meta Reality Labs ； facebookresearch（Facebook Research） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments CVPR 2025

DRO: Doppler-Aware Direct Radar Odometry

Cedric Le Gentil, Leonardo Brizi, Daniil Lisus, Xinyuan Qiao, Giorgio Grisetti, Timothy D. Barfoot

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted for presentation at RSS 2025

WLTCL: Wide Field-of-View 3-D LiDAR Truck Compartment Automatic Localization System

Guodong Sun, Mingjing Li, Dingjie Liu, Mingxuan Liu, Bo Wu, Yang Zhang

机构 * School of Mechanical Engineering, Hubei University of Technology（湖北工业大学机械工程学院） ； Hubei Key Laboratory of Modern Manufacturing Quality Engineering, Hubei University of Technology（湖北工业大学现代制造质量工程重点实验室） ； Shanghai Advanced Research Institute, Chinese Academy of Sciences（中国科学院上海先进研究院） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments To appear in IEEE TIM

Semantic Segmentation and Scene Reconstruction of RGB-D Image Frames: An End-to-End Modular Pipeline for Robotic Applications

Zhiwu Zheng, Lauren Mentzer, Berk Iskender, Michael Price, Colm Prendergast, Audren Cloitre

机构 * Analog Garage, Analog Devices, Inc.（Analog Garage，Analog Devices 公司） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision

Zihui Zhang, Yafei Yang, Hongtao Wen, Bo Yang

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments ICLR 2025 Spotlight. Code and data are available at: https://github.com/vLAR-group/GrabS

MARVIS: Motion & Geometry Aware Real and Virtual Image Segmentation

Jiayi Wu, Xiaomin Lin, Shahriar Negahdaripour, Cornelia Fermüller, Yiannis Aloimonos

专题命中 点云 ：3D reconstruction(abstract)；分类 cs.CV、cs.RO

GarmentTracking: Category-Level Garment Pose Tracking

Han Xue, Wenqiang Xu, Jieyi Zhang, Tutian Tang, Yutong Li, Wenxin Du, Ruolin Ye, Cewu Lu

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments CVPR 2023

Reliable-loc: Robust sequential LiDAR global localization in large-scale street scenes based on verifiable cues

Xianghong Zou, Jianping Li, Weitong Wu, Fuxun Liang, Bisheng Yang, Zhen Dong

专题命中 点云 ：point cloud(abstract)；分类 cs.CV、cs.RO