3D 视觉

Redefining Radar Segmentation: Simultaneous Static-Moving Segmentation and Ego-Motion Estimation using Radar Point Clouds

重新定义雷达分割：利用雷达点云实现同时静态-移动分割和自主运动估计

Simin Zhu, Satish Ravindran, Alexander Yarovoy, Francesco Fioranelli

机构 * Microwave Sensing, Signals and Systems (MS3) group, Delft University of Technology（微波传感、信号与系统（MS3）组，代尔夫特理工大学） ； NXP Semiconductors（NXP半导体公司） 纠错

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

AI总结 本研究提出一种基于神经网络的方法，利用雷达点云同时实现静态-移动分割和自主运动估计，无需中间信号处理步骤。

Comments 16 pages, 9 figures, under review at IEEE Transactions on Radar Systems

DAGLFNet: Deep Feature Attention Guided Global and Local Feature Fusion for Pseudo-Image Point Cloud Segmentation

DAGLFNet：基于伪图像的深度特征注意力引导的全局和局部特征融合用于伪图像点云分割

Chuang Chen, Yi Lin, Bo Wang, Jing Hu, Xi Wu, Wenyi Ge

机构 * College of Computer Science, Chengdu University of Information Technology（成都信息科技大学计算机学院） ； College of Computer Science, Sichuan University（四川大学计算机学院） ； Publications Department, Optica Publishing Group（Optica出版社出版部） ； Department of Electronic Journals, Optica Publishing Group（Optica出版社电子期刊部） 纠错

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

AI总结 DAGLFNet通过深度特征注意力引导的全局和局部特征融合，提升伪图像点云分割的准确性和效率。

Label-Free Model Failure Detection for Lidar-based Point Cloud Segmentation

无需标签的激光雷达点云分割模型失效检测

Daniel Bogdoll, Finn Sartoris, Vincent Geppert, Svetlana Pavlitska, J. Marius Zöllner

机构 * FZI Research Center for Information Technology, Germany（德国弗赖堡信息科技研究中心） ； Karlsruhe Institute of Technology, Germany（德国卡尔斯鲁厄理工学院） 纠错

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

AI总结 本文提出了一种无需标签的激光雷达点云分割模型失效检测方法，利用大规模无标签数据进行监督和自监督学习，引入LidarCODA数据集用于失效模式分析。

Comments Daniel Bogdoll, Finn Sartoris, and Vincent Geppert contributed equally. Accepted for publication at IV 2025

Multiview point cloud registration with anisotropic and space-varying localization noise

多视角点云配准与各向异性及空间变化的定位噪声

Denis Fortun, Etienne Baudrier, Fabian Zwettler, Markus Sauer, Sylvain Faisan

机构 * ICube - UMR7357, CNRS, University of Strasbourg（斯特拉斯堡大学） ； Lehrstuhl für Biotechnologie und Biophysik, Biozentrum, Universität Würzburg, Germany（乌尔姆大学） 纠错

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

AI总结 本文提出一种处理多视角点云配准中各向异性及空间变化定位噪声的方法，通过显式噪声模型提升鲁棒性，并在模拟和真实数据上验证效果。

Journal ref SIAM Journal on Imaging Sciences, 2025, 18(1), pp.280-307

Rethinking the Encoding and Annotating of 3D Bounding Box: Corner-Aware 3D Object Detection from Point Clouds

重新思考3D边界框的编码与标注：从点云中基于角点的3D目标检测

Qinghao Meng, Junbo Yin, Jianbing Shen, Yunde Jia

机构 * School of Computer Science, Beijing Institute of Technology（计算机科学学院，北京理工大学） ； Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, Center of Excellence for Smart Health, and Center of Excellence for Generative AI, King Abdullah University of Science and Technology (KAUST)（计算机科学项目，计算机、电气和数学科学与工程（CEMSE）部门，智能健康卓越中心，生成人工智能卓越中心，国王阿卜杜勒·阿齐兹大学科学与技术（KAUST）） ； State Key Laboratory of Internet of Things for Smart City, Department of Computer and Information Science, University of Macau（智慧城市物联网国家重点实验室，澳门大学计算机与信息科学系） ； Guangdong Provincial Key Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University（广东省机器感知与智能计算重点实验室，深圳MSU-BIT大学） ； Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology（北京智能信息技术重点实验室，计算机科学学院，北京理工大学） 纠错

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

AI总结 本文提出基于角点的3D目标检测方法，通过角点对齐回归提升检测性能，仅需BEV角点点击即可达到接近全监督的准确率。

Comments 8 pages, 5 figures, 2 tables

CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking

CompTrack: 基于信息瓶颈的点云跟踪低秩动态令牌压缩

Sifan Zhou, Yichao Cao, Jiahao Nie, Yuqian Fu, Ziyu Zhao, Xiaobo Lu, Shuo Wang

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

AI总结 CompTrack通过信息瓶颈引导的低秩动态令牌压缩技术，有效解决点云中空间和信息冗余问题，实现高效实时的三维单目标跟踪。

Comments Accepted by AAAI 2026 (Oral)

RL-AD-Net: Reinforcement Learning Guided Adaptive Displacement in Latent Space for Refined Point Cloud Completion

RL-AD-Net: 基于强化学习的潜在空间自适应位移用于精细化点云补全

Bhanu Pratap Paregi, Vaibhav Kumar

机构 * GeoAI4Cities Lab, IISER Bhopal（GeoAI4Cities实验室，印度Bhopal IISER） 纠错

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

AI总结 RL-AD-Net通过强化学习在潜在空间中优化点云补全，提升局部几何一致性，适用于多种补全网络。

Real-time Point Cloud Data Transmission via L4S for 5G-Edge-Assisted Robotics

通过L4S实现5G边缘辅助机器人中的实时点云数据传输

Gerasimos Damigos, Achilleas Santi Seisa, Nikolaos Stathoulopoulos, Sara Sandberg, George Nikolakopoulos

机构 * Ericsson Research, Lule , Sweden ( ) ； AI Group, Lule \, University of Technology, Sweden 纠错

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

AI总结 本文提出了一种基于L4S的实时点云传输框架，通过Draco压缩算法实现低延迟、低丢包率的3D LiDAR数据传输，适用于5G边缘辅助机器人中的实时数据处理与SLAM算法验证。

Comments IFAC Submission

Point Cloud Quantization through Multimodal Prompting for 3D Understanding

Hongxuan Li, Wencheng Zhu, Huiying Xu, Xinzhong Zhu, Pengfei Zhu

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

Comments Accepted by AAAI 2026. 11 pages, 7 figures

PointVDP: Learning View-Dependent Projection by Fireworks Rays for 3D Point Cloud Segmentation

Yang Chen, Yueqi Duan, Haowen Sun, Ziwei Wang, Jiwen Lu, Yap-Peng Tan

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

Comments This version needs major revision

Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction

Xinzhu Ma, Cheng Wang, Chen Tang, Bin Wang, Shixiang Tang, Yuan Meng, Yunhong Wang, Di Huang

机构 * Beihang University（北航大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Wuhan University（武汉大学） ； The Chinese University of Hong Kong（香港中文大学） ； Tsinghua University（清华大学） 纠错

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

Deep Imbalanced Multi-Target Regression: 3D Point Cloud Voxel Content Estimation in Simulated Forests

Amirhossein Hassanzadeh, Bartosz Krawczyk, Michael Saunders, Rob Wible, Keith Krause, Dimah Dera, Jan van Aardt

机构 * United State Space Force（美国太空军） ； Battelle（巴特尔） 纠错

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

Comments This work has been submitted to the IEEE for possible publication

DANCE: Density-agnostic and Class-aware Network for Point Cloud Completion

Da-Yeong Kim, Yeong-Jun Cho

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

Comments 7 pages, 11 figures, Accepted to AAAI 2026 (to appear)

Density-aware global-local attention network for point cloud segmentation

Chade Li, Pengju Zhang, Jiaming Zhang, Yihong Wu

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院，北京100190，中国） ； School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China（人工智能学院，中国科学院大学，北京100049，中国） 纠错

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

Comments Accepted by Image and Vision Computing

Journal ref Image and Vision Computing, Volume 165, 2026, 105822

Refining Segmentation On-the-Fly: An Interactive Framework for Point Cloud Semantic Segmentation

Peng Zhang, Ting Wu, Jinsheng Sun, Weiqing Li, Zhiyong Su

机构 * Nanjing University of Science and Technology（南京理工大学） 纠错

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

Journal ref Engineering Applications of Artificial Intelligence, Volume 163, Part 2, 1 January 2026, 112919

EPSegFZ: Efficient Point Cloud Semantic Segmentation for Few- and Zero-Shot Scenarios with Language Guidance

Jiahui Wang, Haiyue Zhu, Haoren Guo, Abdullah Al Mamun, Cheng Xiang, Tong Heng Lee

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

Comments AAAI 2026

Multi-view Structural Convolution Network for Domain-Invariant Point Cloud Recognition of Autonomous Vehicles

Younggun Kim, Mohamed Abdel-Aty, Beomsik Cho, Seonghoon Ryoo, Soomok Lee

机构 * Department of Civil Engineering, University of Central Florida（中央佛罗里达大学土木工程系） ； Department of Data, Networks and AI, Ajou University（全州大学数据、网络与人工智能系） ； Department of Mobility Engineering and Department of Artificial Intelligence, Ajou University（全州大学移动工程系和人工智能系） 纠错

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

Comments 16 pages, 6 figures

RWKV-PCSSC: Exploring RWKV Model for Point Cloud Semantic Scene Completion

Wenzhe He, Xiaojun Chen, Wentang Chen, Hongyu Wang, Ying Liu, Ruihui Li

机构 * Hunan University College of Computer Science（湖南大学计算机科学学院） ； Hunan Normal University College of Information Science（湖南师范大学信息科学学院） ； Hunan University（湖南大学） ； Hunan Normal University（湖南师范大学） 纠错

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

Comments 13 pages, 8 figures, published to ACM MM

Journal ref Proc. 33rd ACM Int. Conf. Multimedia (MM '25), Dublin, Ireland, 2025, pp. 161-170

UMIGen: A Unified Framework for Egocentric Point Cloud Generation and Cross-Embodiment Robotic Imitation Learning

Yan Huang, Shoujie Li, Xingting Li, Wenbo Ding

机构 * Shenzhen International Graduate School, Tsinghua University（深圳国际研究生院，清华大学） 纠错

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

OG-PCL: Efficient Sparse Point Cloud Processing for Human Activity Recognition

Jiuqi Yan, Chendong Xu, Dongyu Liu

机构 * Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education, Southeast University, Nanjing, 211189, China（教育部水下声学信号处理重点实验室，东南大学，南京） 纠错

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

Multi-Modal Assistance for Unsupervised Domain Adaptation on Point Cloud 3D Object Detection

Shenao Zhao, Pengpeng Liang, Zhoufan Yang

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

Comments Accepted to AAAI-26

CloudMamba: Grouped Selective State Spaces for Point Cloud Analysis

Kanglin Qu, Pan Gao, Qun Dai, Zhanzhi Ye, Rui Ye, Yuanhao Sun

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

Comments Accepted by AAAI '26

Certified L2-Norm Robustness of 3D Point Cloud Recognition in the Frequency Domain

Liang Zhou, Qiming Wang, Tianze Chen

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

Comments Accepted by AAAI26

PointCubeNet: 3D Part-level Reasoning with 3x3x3 Point Cloud Blocks

Da-Yeong Kim, Yeong-Jun Cho

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

Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point clouds

Lassi Ruoppa, Oona Oinonen, Josef Taher, Matti Lehtomäki, Narges Takhtkeshha, Antero Kukko, Harri Kaartinen, Juha Hyyppä

机构 * Department of Remote Sensing and Photogrammetry, Finnish Geospatial Research Institute FGI, The National Land Survey of Finland（遥感与摄影测量系，芬兰地理研究 institute FGI，芬兰国家土地测绘局） ； D Optical Metrology (3DOM) unit, Bruno Kessler Foundation (FBK)（3D光学计量（3DOM）单元，布鲁诺·凯瑟尔基金会（FBK）） ； Department of Built Environment, Aalto University, School of Engineering（环境学院，艾尔托大学，工程学院） 纠错

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

Comments 30 pages, 10 figures

Journal ref ISPRS Journal of Photogrammetry and Remote Sensing, Volume 228, 2025, pages 694-722

Adaptive Agent Selection and Interaction Network for Image-to-point cloud Registration

Zhixin Cheng, Xiaotian Yin, Jiacheng Deng, Bohao Liao, Yujia Chen, Xu Zhou, Baoqun Yin, Tianzhu Zhang

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

Comments Accepted by AAAI2026

Point Cloud Segmentation of Integrated Circuits Package Substrates Surface Defects Using Causal Inference: Dataset Construction and Methodology

Bingyang Guo, Qiang Zuo, Ruiyun Yu

机构 * Bingyang Guo, Qiang Zuo, Ruiyun Yu（作者） 纠错

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

IEC3D-AD: A 3D Dataset of Industrial Equipment Components for Unsupervised Point Cloud Anomaly Detection

Bingyang Guo, Hongjie Li, Ruiyun Yu, Hanzhe Liang, Jinbao Wang

机构 * Software College, Northeastern University（东北大学软件学院） ； Shenzhen Audencia Financial Technology Institute, Shenzhen University（深圳Audencia金融技术研究院） ； National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University（深圳大学大数据系统计算技术国家工程实验室） 纠错

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

From Propagation to Prediction: Point-level Uncertainty Evaluation of MLS Point Clouds under Limited Ground Truth

Ziyang Xu, Olaf Wysocki, Christoph Holst

机构 * Chair of Engineering Geodesy, TUM School of Engineering and Design, Technical University of Munich（工程测绘学系，技术大学慕尼黑工程与设计学院） ； TUM Leonhard Obermeyer Center, Technical University of Munich（技术大学慕尼黑Leonhard Obermeyer中心） ； CV4DT, University of Cambridge（剑桥大学CV4DT） 纠错

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

A Novel Grouping-Based Hybrid Color Correction Algorithm for Color Point Clouds

Kuo-Liang Chung, Ting-Chung Tang

机构 * Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology（计算机科学与信息工程系，国立台湾科技大学） 纠错

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