3D 视觉

Topology-Guided Knowledge Distillation for Efficient Point Cloud Processing

Luu Tung Hai, Thinh D. Le, Zhicheng Ding, Qing Tian, Truong-Son Hy

机构 * The University of Alabama at Birmingham（亚拉巴马大学伯明翰分校） ； Soongsil University（顺斯尔大学） ； Bowling Green State University（伯灵顿州立大学） 纠错

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

Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly Detection

Yuqi Cheng, Yunkang Cao, Dongfang Wang, Weiming Shen, Wenlong Li

机构 * State Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology（智能制造装备与技术国家重点实验室，华中科技大学） 纠错

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

Comments 12 pages, 12 figures

PillarMamba: Learning Local-Global Context for Roadside Point Cloud via Hybrid State Space Model

Zhang Zhang, Chao Sun, Chao Yue, Da Wen, Tianze Wang, Jianghao Leng

机构 * National Engineering Laboratory for Electric Vehicles, School of Mechanical Engineering, Beijing Institute of Technology（电动汽车国家工程实验室，机械工程学院，北京理工大学） 纠错

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

PointBA: Towards Backdoor Attacks in 3D Point Cloud

Xinke Li, Zhirui Chen, Yue Zhao, Zekun Tong, Yabang Zhao, Andrew Lim, Joey Tianyi Zhou

机构 * National University of Singapore（新加坡国立大学） ； Southwest Jiaotong University（西南交通大学） ； Institute of High Performance Computing, A*STAR（高性能计算研究所，A*STAR） 纠错

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

Comments Accepted by ICCV 2021

3D Can Be Explored In 2D: Pseudo-Label Generation for LiDAR Point Clouds Using Sensor-Intensity-Based 2D Semantic Segmentation

Andrew Caunes, Thierry Chateau, Vincent Frémont

机构 * Logiroad ； LS2N - Ecole Centrale de Nantes（LS2N - 纵向神经网络） 纠错

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

Comments Accepted to IV2024

Enhancing Lidar Point Cloud Sampling via Colorization and Super-Resolution of Lidar Imagery

Sier Ha, Honghao Du, Xianjia Yu, Tomi Westerlund

机构 * Turku Intelligent Embedded and Robotic Systems (TIERS) Lab, University of Turku, Finland（图尔库智能嵌入式与机器人系统实验室，图尔库大学，芬兰） 纠错

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

Comments 7 pages. arXiv admin note: substantial text overlap with arXiv:2409.11532

Tightly Coupled Range Inertial Odometry and Mapping with Exact Point Cloud Downsampling

Kenji Koide, Aoki Takanose, Shuji Oishi, Masashi Yokozuka

机构 * Department of Information Technology and Human Factors, the National Institute of Advanced Industrial Science and Technology（信息科技与人因工程系，国家先进工业科学与技术研究院） 纠错

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

Comments IEEE International Conference on Robotics and Automation (ICRA2025)

F2M-Reg: Unsupervised RGB-D Point Cloud Registration with Frame-to-Model Optimization

Zhinan Yu, Zheng Qin, Yijie Tang, Yongjun Wang, Renjiao Yi, Chenyang Zhu, Kai Xu

机构 * National University of Defense Technology（国防科技大学） ； Xiangjiang Laboratory（湘江实验室） ； Defense Innovation Institute, Academy of Military Sciences（国防科技创新院） 纠错

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

Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning

Yabin Zhang, Jiehong Lin, Ruihuang Li, Kui Jia, Lei Zhang

机构 * Department of Computing, The Hong Kong Polytechnic University（计算系，香港理工大学） ； School of Electronic and Information Engineering, South China University of Technology（电子与信息工程学院，华南理工大学） 纠错

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

Comments Journal revision; Codes are available at \url{https://github.com/YBZh/Point-DAE}

Journal ref IEEE Transactions on Neural Networks and Learning Systems 2025

Path Planning on Multi-level Point Cloud with a Weighted Traversability Graph

Yujie Tang, Quan Li, Hao Geng, Yangmin Xie, Hang Shi, Yusheng Yang

机构 * School of Mechatronics Engineering and Automation, Shanghai University（上海大学机械与自动化工程学院） ； Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, Shanghai University（上海大学智能制造与机器人重点实验室） ； Areaspace Information Research Institute, Chinese Academy of Sciences（中国科学院空域信息研究所） 纠错

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

Multiview Point Cloud Registration via Optimization in an Autoencoder Latent Space

Luc Vedrenne, Sylvain Faisan, Denis Fortun

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

Comments 14 pages, 19 figures, IEEE Transactions on Image Processing

Autoencoder Models for Point Cloud Environmental Synthesis from WiFi Channel State Information: A Preliminary Study

Daniele Pannone, Danilo Avola

机构 * Department of Computer Science, Sapienza University of Rome（西尔维娅大学罗马计算机科学系） 纠错

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

NoPain: No-box Point Cloud Attack via Optimal Transport Singular Boundary

Zezeng Li, Xiaoyu Du, Na Lei, Liming Chen, Weimin Wang

机构 * School of Software, Dalian University of Technology（大连理工大学软件学院） ； École Centrale de Lyon（里昂中央理工大学） ； University of Lyon（里昂大学） ； Institut Universitaire de France（法国高等科学研究院） 纠错

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

Point2Quad: Generating Quad Meshes from Point Clouds via Face Prediction

Zezeng Li, Zhihui Qi, Weimin Wang, Ziliang Wang, Junyi Duan, Na Lei

机构 * School of Software Technology and the DUT-RU International School of Information Science and Engineering（软件技术学院和大连理工大学-俄罗斯国际信息科学与工程学院） 纠错

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

Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis

Hongyu Sun, Qiuhong Ke, Ming Cheng, Yongcai Wang, Deying Li, Chenhui Gou, Jianfei Cai

机构 * Department of Computer Science, Renmin University of China（中国人民大学计算机学院） ； Department of Data Science & AI, Monash University（墨尔本大学数据科学与人工智能系） 纠错

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

Comments Accepted by CVPR 2025; 24 pages, 14 figures, 18 tables

P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds

Jiahao Nie, Fei Xie, Sifan Zhou, Xueyi Zhou, Dong-Kyu Chae, Zhiwei He

机构 * Hangzhou Dianzi University（杭州电子科技大学） ； Shanghai Jiao Tong University（上海交通大学） ； Carnegie Mellon University（卡内基梅隆大学） ； Hanyang University（翰阳大学） 纠错

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

Comments Accept by IJCV

BPNet: Bézier Primitive Segmentation on 3D Point Clouds

Rao Fu, Cheng Wen, Qian Li, Xiao Xiao, Pierre Alliez

机构 * Inria（法国国家信息与自动化技术研究院） ； Geometry Factory（几何工厂） ； The University of Sydney（悉尼大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

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

Journal ref In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, pages 754-762, 2023

Locating and Mitigating Gradient Conflicts in Point Cloud Domain Adaptation via Saliency Map Skewness

Jiaqi Tang, Yinsong Xu, Qingchao Chen

机构 * National Institute of Health Data Science, Peking University（北京大学国家健康数据科学研究院） ； Institute of Medical Technology, Peking University（北京大学医学技术研究院） ； State Key Laboratory of General Artificial Intelligence, Peking University（北京大学通用人工智能国家重点实验室） ； School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院） 纠错

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

Efficient Implicit Neural Compression of Point Clouds via Learnable Activation in Latent Space

Yichi Zhang, Qianqian Yang

机构 * Zhejiang University（浙江大学） 纠错

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

Comments 8 pages

ROI-Guided Point Cloud Geometry Compression Towards Human and Machine Vision

Xie Liang, Gao Wei, Zhenghui Ming, Li Ge

机构 * Peking University Shenzhen Graduate School and Peng Cheng Laboratory（北京大学深圳研究生院和鹏城实验室） 纠错

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

Comments 10 pages, 5 figures

Journal ref ACM International Conference on Multimedia 2024

HFBRI-MAE: Handcrafted Feature Based Rotation-Invariant Masked Autoencoder for 3D Point Cloud Analysis

Xuanhua Yin, Dingxin Zhang, Jianhui Yu, Weidong Cai

机构 * School of Computer Science, The University of Sydney（计算机科学学院，悉尼大学） 纠错

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

Comments 12 pages, 9 figures, accepted by IJCNN 2025

RefComp: A Reference-guided Unified Framework for Unpaired Point Cloud Completion

Yixuan Yang, Jinyu Yang, Zixiang Zhao, Victor Sanchez, Feng Zheng

机构 * Southern University of Science and Technology（南方科技大学） ； University of Warwick（沃里克大学） ； Photogrammetry and Remote Sensing, ETH Zürich（摄影测量与遥感，苏黎世联邦理工学院） 纠错

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

ViG3D-UNet: Volumetric Vascular Connectivity-Aware Segmentation via 3D Vision Graph Representation

Bowen Liu, Chunlei Meng, Wei Lin, Hongda Zhang, Ziqing Zhou, Zhongxue Gan, Chun Ouyang

机构 * Academy for Engineering and Technology, Fudan University（复旦大学工程与技术学院） 纠错

专题命中 点云 ：3D vision(title,abstract)；分类 cs.CV

DG-MVP: 3D Domain Generalization via Multiple Views of Point Clouds for Classification

Huantao Ren, Minmin Yang, Senem Velipasalar

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

3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap

Minmin Yang, Huantao Ren, Senem Velipasalar

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

Non-uniform Point Cloud Upsampling via Local Manifold Distribution

Yaohui Fang, Xingce Wang

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

Intelligent driving vehicle front multi-target tracking and detection based on YOLOv5 and point cloud 3D projection

Dayong Liu, Qingrui Zhang, Zeyang Meng

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

Comments in Chinese language

PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Model

Hao Yang, Qianyu Zhou, Haijia Sun, Xiangtai Li, Fengqi Liu, Xuequan Lu, Lizhuang Ma, Shuicheng Yan

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

Comments Published on Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2025;

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 39(9), 9193-9201, 2025

Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attacks

Haosheng Li, Junjie Chen, Yuecong Xu, Kemi Ding

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

ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentation

Haosheng Li, Yuecong Xu, Junjie Chen, Kemi Ding

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