3D 视觉

R2LDM: An Efficient 4D Radar Super-Resolution Framework Leveraging Diffusion Model

Boyuan Zheng, Shouyi Lu, Renbo Huang, Minqing Huang, Fan Lu, Wei Tian, Guirong Zhuo, Lu Xiong

机构 * School of Automotive Studies, Tongji University（汽车学院，同济大学） 纠错

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

Comments 8 pages, 9 figures, accepted to IROS 2025

Vision-based Lifting of 2D Object Detections for Automated Driving

Hendrik Königshof, Kun Li, Christoph Stiller

机构 * Intel. Systems and Prod. Engineering（英特尔系统与生产工程） ； FZI Research Center for Inf. Technology（弗劳恩霍夫研究所信息技术研究中心） ； Institute of Meas. and Control Systems（测量与控制系统研究所） ； Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院） 纠错

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

Comments https://ieeexplore.ieee.org/document/9190325

Journal ref 2020 IEEE 23rd International Conference on Information Fusion (FUSION)

DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning

Weikang Wan, Ziyu Wang, Yufei Wang, Zackory Erickson, David Held

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

Comments NeurIPS 2024 (Spotlight)

Hierarchical Error Assessment of CAD Models for Aircraft Manufacturing-and-Measurement

Jin Huang, Honghua Chen, Mingqiang Wei

机构 * School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院） ； School of Artificial Intelligence, Taiyuan University of Technology（太原科技大学人工智能学院） ； College of Computing and Data Science, Nanyang Technological University (NTU)（南洋理工大学计算机科学与数据科学学院） 纠错

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

PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets

Ali Kashefi

机构 * Cranberry-Lemon University（Cranberry-Lemon 大学） ； University of the Witwatersrand（威特沃特斯兰大学） ； Stanford University（斯坦福大学） 纠错

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

Boosting 3D Object Detection with Semantic-Aware Multi-Branch Framework

Hao Jing, Anhong Wang, Lijun Zhao, Yakun Yang, Donghan Bu, Jing Zhang, Yifan Zhang, Junhui Hou

机构 * School of Electronic Information Engineering, Taiyuan University of Science and Technology（太原科技大学电子信息工程学院） ； Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系） 纠错

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

Journal ref IEEE Transactions on Circuits and Systems for Video Technology, Vol. 35, No. 6, pp. 5697-5710, 2025

AugmentGest: Can Random Data Cropping Augmentation Boost Gesture Recognition Performance?

Nada Aboudeshish, Dmitry Ignatov, Radu Timofte

机构 * Computer Vision Lab, CAIDAS, University of Würzburg, Germany（计算机视觉实验室，CAIDAS，乌尔姆大学） 纠错

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

Towards Terrain-Aware Task-Driven 3D Scene Graph Generation in Outdoor Environments

Chad R Samuelson, Timothy W McLain, Joshua G Mangelson

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

Comments Presented at the 2025 IEEE ICRA Workshop on Field Robotics

Pts3D-LLM: Studying the Impact of Token Structure for 3D Scene Understanding With Large Language Models

Hugues Thomas, Chen Chen, Jian Zhang

机构 * Apple（苹果公司） 纠错

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

Comments Main paper and appendix

Through-the-Wall Radar Human Activity Recognition WITHOUT Using Neural Networks

Weicheng Gao

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

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

Comments 15 pages, 8 figures, 8 tables

OpenMaskDINO3D : Reasoning 3D Segmentation via Large Language Model

Kunshen Zhang

机构 * Wuhan University（武汉大学） 纠错

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

Comments Project Page: https://github.com/Zhangkuns/OpenMaskDINO3D

Follow-Your-Creation: Empowering 4D Creation through Video Inpainting

Yue Ma, Kunyu Feng, Xinhua Zhang, Hongyu Liu, David Junhao Zhang, Jinbo Xing, Yinhan Zhang, Ayden Yang, Zeyu Wang, Qifeng Chen

机构 * HKUST（香港科技大学） ； HKUST(GZ)（香港科技大学（广州）） ； NUS（国立新加坡大学） ； Tsinghua Univerisity（清华大学） ； CUHK（香港中文大学） 纠错

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

Comments Project Page: https://follow-your-creation.github.io/

Understanding and Mitigating Network Latency Effect on Teleoperated-Robot with Extended Reality

Ziliang Zhang, Cong Liu, Hyoseung Kim

机构 * University of California, Riverside（加州大学河滨分校） 纠错

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

Comments This documents is a 5 pages technical report version. Removed watermark from acm for copyright purpose

SuperMapNet for Long-Range and High-Accuracy Vectorized HD Map Construction

Ruqin Zhou, Chenguang Dai, Wanshou Jiang, Yongsheng Zhang, Hanyun Wang, San Jiang

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

Comments 13 pages, 9 figures

EV-Flying: an Event-based Dataset for In-The-Wild Recognition of Flying Objects

Gabriele Magrini, Federico Becattini, Giovanni Colombo, Pietro Pala

机构 * University of Florence（佛罗伦萨大学） ； University of Siena（锡耶纳大学） 纠错

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

Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision

Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura, Shinsuke Mori

机构 * Kyoto University（京都大学） ； National Institute of Informatics（国家信息研究所） ； Sony Interactive Entertainment（索尼互动娱乐） 纠错

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

Comments CVPR 2025

Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather

Longyu Yang, Ping Hu, Shangbo Yuan, Lu Zhang, Jun Liu, Hengtao Shen, Xiaofeng Zhu

机构 * UESTC（电子科技大学） ； DLUT（大连理工大学） ； Lancaster University（兰卡斯特大学） ； Tongji University（同济大学） 纠错

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

PointCloud-Text Matching: Benchmark Datasets and a Baseline

Yanglin Feng, Yang Qin, Dezhong Peng, Hongyuan Zhu, Xi Peng, Peng Hu

机构 * College of Computer Science, Sichuan University（四川大学计算机学院） ； Sichuan National Innovation New Vision UHD Video Technology Co., Ltd（四川创新新视野UHD视频技术有限公司） ； Institute for Infocomm Research (I 2 R), A*STAR（信息通信研究院（I2R），A*STAR） 纠错

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

Comments The version submitted this time has been significantly revised and improved on the previous version

MR2US-Pro: Prostate MR to Ultrasound Image Translation and Registration Based on Diffusion Models

Xudong Ma, Nantheera Anantrasirichai, Stefanos Bolomytis, Alin Achim

机构 * Visual Information Laboratory, University of Bristol（布里斯托大学视觉信息实验室） ； Southmead Hospital, North Bristol NHS Trust（北布里斯托NHS信托南梅德医院） 纠错

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

Deformable registration and generative modelling of aortic anatomies by auto-decoders and neural ODEs

Riccardo Tenderini, Luca Pegolotti, Fanwei Kong, Stefano Pagani, Francesco Regazzoni, Alison L. Marsden, Simone Deparis

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

Comments 29 pages, 7 figures, 6 tables, 2 algorithms. Submitted to "npj Biological Physics and Mechanics". Dataset publicly available at https://doi.org/10.5281/zenodo.15494901

Improving Multi-Vehicle Perception Fusion with Millimeter-Wave Radar Assistance

Zhiqing Luo, Yi Wang, Yingying He, Wei Wang

机构 * Huazhong University of Science and Technology（华中科技大学） 纠错

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

Comments to appear in IEEE INFOCOM 2025

Constrained Stein Variational Gradient Descent for Robot Perception, Planning, and Identification

Griffin Tabor, Tucker Hermans

机构 * University of Utah Robotics Center（犹他大学机器人中心） ； NVIDIA（英伟达） 纠错

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

NUC-Net: Non-uniform Cylindrical Partition Network for Efficient LiDAR Semantic Segmentation

Xuzhi Wang, Wei Feng, Lingdong Kong, Liang Wan

机构 * College of Computer and Information Engineering, Tianjin Normal University（天津师范大学计算机与信息工程学院） ； Tianjin Key Laboratory of Student Mental Health and Intelligence Assessment（天津学生心理健康与智能评估重点实验室） ； College of Intelligence and Computing, Tianjin University（天津大学智能与计算学院） ； Department of Computer Science, National University of Singapore（新加坡国立大学计算机科学系） 纠错

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

Comments Accepted at TCSVT in 2025.Code available at https://github.com/alanWXZ/NUC-Net

Railway LiDAR semantic segmentation based on intelligent semi-automated data annotation

Florian Wulff, Bernd Schaeufele, Julian Pfeifer, Ilja Radusch

机构 * Fraunhofer Institute for Open Communication Technologies (FOKUS)（弗劳恩霍夫开放通信技术研究所） ； Daimler Center for Automotive Information Technology Innovations (DCAITI)（戴姆勒汽车信息技术创新中心） 纠错

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

Comments This article has been accepted for publication in the IEEE VTC Fall 2024

EasyREG: Easy Depth-Based Markerless Registration and Tracking using Augmented Reality Device for Surgical Guidance

Yue Yang, Christoph Leuze, Brian Hargreaves, Bruce Daniel, Fred Baik

机构 * Stanford University（斯坦福大学） 纠错

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

GenCAD-Self-Repairing: Feasibility Enhancement for 3D CAD Generation

Chikaha Tsuji, Enrique Flores Medina, Harshit Gupta, Md Ferdous Alam

机构 * Massachusetts Institute of Technology（麻省理工学院） 纠错

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

DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation

Peiqi Liu, Zhanqiu Guo, Mohit Warke, Soumith Chintala, Chris Paxton, Nur Muhammad Mahi Shafiullah, Lerrel Pinto

机构 * New York University（纽约大学） ； Meta Inc.（Meta公司） ； Hello Robot Inc.（Hello Robot公司） 纠错

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

Comments Website: https://dynamem.github.io

LiDARDustX: A LiDAR Dataset for Dusty Unstructured Road Environments

Chenfeng Wei, Qi Wu, Si Zuo, Jiahua Xu, Boyang Zhao, Zeyu Yang, Guotao Xie, Shenhong Wang

机构 * Wuxi Intelligent Control Research Institute,HNU（无锡智能控制研究院，湖南大学） ； Hunan University（湖南大学） ； Tsinghua University（清华大学） ； Xi’an Jiaotong-Liverpool University（西安交通大学利物浦大学） 纠错

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

Knowledge Distillation Approach for SOS Fusion Staging: Towards Fully Automated Skeletal Maturity Assessment

Omid Halimi Milani, Amanda Nikho, Marouane Tliba, Lauren Mills, Ahmet Enis Cetin, Mohammed H Elnagar

机构 * Department of Electrical and Computer Engineering, University of Illinois Chicago（伊利诺伊大学芝加哥分校电气与计算机工程系） ； Department of Orthodontics, College of Dentistry, University of Illinois Chicago（伊利诺伊大学芝加哥分校牙科学院正畸学系） ； University of Orleans（奥尔良大学） 纠错

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

Comments This paper has been accepted to the CVPR Workshop 2025, to be held in Nashville, Tennessee

Functionality understanding and segmentation in 3D scenes

Jaime Corsetti, Francesco Giuliari, Alice Fasoli, Davide Boscaini, Fabio Poiesi

机构 * Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会） ； University of Trento（特伦托大学） 纠错

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

Comments CVPR 2025 Highlight. Camera ready version. 20 pages, 12 figures, 7 tables. Fixed typo in Eq.2