3D 视觉

Textured As-Is BIM via GIS-informed Point Cloud Segmentation

Mohamed S. H. Alabassy

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

Comments Permission granted by all co-authors for the publication of the extended article to the conference paper "BIM Integration for Automated Identification of Relevant Geo-Context Information via Point Cloud Segmentation" (2023). URL: https://www.ucl.ac.uk/bartlett/construction/sites/bartlett_construction/files/bim_integration_for_automated_identification_of_relevant_geo-context.pdf

PX2Tooth: Reconstructing the 3D Point Cloud Teeth from a Single Panoramic X-ray

Wen Ma, Huikai Wu, Zikai Xiao, Yang Feng, Jian Wu, Zuozhu Liu

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

Comments Ma W, Wu H, Xiao Z, et al. PX2Tooth: Reconstructing the 3D Point Cloud Teeth from a Single Panoramic X-Ray[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer Nature Switzerland, 2024: 411-421

Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning

Bin Ren, Guofeng Mei, Danda Pani Paudel, Weijie Wang, Yawei Li, Mengyuan Liu, Rita Cucchiara, Luc Van Gool, Nicu Sebe

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

Comments Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning

Points for Energy Renovation (PointER): A LiDAR-Derived Point Cloud Dataset of One Million English Buildings Linked to Energy Characteristics

Sebastian Krapf, Kevin Mayer, Martin Fischer

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

Comments The PointER dataset can be downloaded from https://doi.org/10.14459/2023mp1713501. The code used for generating building point clouds is available at https://github.com/kdmayer/PointER

Joint Geometry and Attribute Upsampling of Point Clouds Using Frequency-Selective Models with Overlapped Support

Viktoria Heimann, Andreas Spruck, André Kaup

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

Comments 10 pages, 10 figures, Under Review at IEEE TMM Special Issue on Point Cloud Processing and Understanding

GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compression

Jiahao Pang, Muhammad Asad Lodhi, Dong Tian

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

Comments Accepted at ACM MM 2022 Workshop on Advances in Point Cloud Compression, Processing and Analysis

Sequential Point Clouds: A Survey

Haiyan Wang, Yingli Tian

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

Comments Survey paper on sequential point clouds

Deep Models with Fusion Strategies for MVP Point Cloud Registration

Lifa Zhu, Changwei Lin, Dongrui Liu, Xin Li, Francisco Gómez-Fernández

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

Comments Point cloud registration competition, ICCV21 workshop. Substantial text overlap with arXiv:2107.02583

Investigating Attention Mechanism in 3D Point Cloud Object Detection

Shi Qiu, Yunfan Wu, Saeed Anwar, Chongyi Li

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

Comments International Conference on 3D Vision (3DV 2021)

Cascaded Refinement Network for Point Cloud Completion with Self-supervision

Xiaogang Wang, Marcelo H Ang, Gim Hee Lee

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

Comments Accepted by PAMI. Extended version of the following paper: Cascaded Refinement Network for Point Cloud Completion. CVPR 2020. arXiv link: arXiv:2004.03327

3D Graph Embedding Learning with a Structure-aware Loss Function for Point Cloud Semantic Instance Segmentation

Zhidong Liang, Ming Yang, Chunxiang Wang

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

Journal ref Title: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation; Published in: IEEE Robotics and Automation Letters ( Volume: 5, Issue: 3, July 2020)

Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks

Junming Zhang, Ming-Yuan Yu, Ram Vasudevan, Matthew Johnson-Roberson

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

Comments 3D Vision Conference 2020

A Progressive Conditional Generative Adversarial Network for Generating Dense and Colored 3D Point Clouds

Mohammad Samiul Arshad, William J. Beksi

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

Comments To be published in the 2020 International Conference on 3D Vision (3DV)

Linking Points With Labels in 3D: A Review of Point Cloud Semantic Segmentation

Yuxing Xie, Jiaojiao Tian, Xiao Xiang Zhu

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

Comments The title of published version was modified to "Linking Points With Labels in 3D: A Review of Point Cloud Semantic Segmentation". To read its final version please go to IEEE Geoscience and Remote Sensing Magazine on IEEE XPlore: https://ieeexplore.ieee.org/document/9028090

ShapeAdv: Generating Shape-Aware Adversarial 3D Point Clouds

Kibok Lee, Zhuoyuan Chen, Xinchen Yan, Raquel Urtasun, Ersin Yumer

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

Comments 3D Point Clouds, Adversarial Learning

Rotation Invariant Convolutions for 3D Point Clouds Deep Learning

Zhiyuan Zhang, Binh-Son Hua, David W. Rosen, Sai-Kit Yeung

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

Comments International Conference on 3D Vision (3DV) 2019

Casualty Detection from 3D Point Cloud Data for Autonomous Ground Mobile Rescue Robots

Roni Permana Saputra, Petar Kormushev

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

Comments Published in SSRR 2018 Conference

Journal ref R. P. Saputra and P. Kormushev, "Casualty Detection from 3D Point Cloud Data for Autonomous Ground Mobile Rescue Robots," 2018 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), Philadelphia, PA, 2018, pp. 1-7

YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud

Waleed Ali, Sherif Abdelkarim, Mohamed Zahran, Mahmoud Zidan, Ahmad El Sallab

专题命中 点云 ：point cloud(title,abstract)；分类 cs.CV；3D reconstruction(comments)

Comments Paper accepted in ECCV 2018, "3D Reconstruction meets Semantics" workshop

A Systematic Approach for Cross-source Point Cloud Registration by Preserving Macro and Micro Structures

Xiaoshui Huang, Jian Zhang, Lixin Fan, Qiang Wu, Chun Yuan

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

Comments Cross-source point cloud registration

IRGNN: Efficient Invariant Radar Graph Neural Network for Radar Point Cloud Object Detection

IRGNN：用于雷达点云目标检测的高效不变雷达图神经网络

Xiao Guo, Wanke Xia, Lili Yang, Caicong Wu

机构 * China Agricultural University（中国农业大学） ； Tsinghua University（清华大学） 纠错

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

AI总结 针对雷达点云稀疏无序、信息不足难以适配现有激光雷达方法的问题，提出IRGNN，通过不变特征设计、改进MPNN及任务头实现目标检测，在RadarScenes数据集上性能更优且推理效率更高。

Comments Accepted at ICONIP 2026

Boundary-Enhanced Segmentation of Pig Point Clouds in Commercial Housing Environments

商业养殖环境下猪只点云的边界增强分割

Zhankang Xu, Fei Shi, Xiangyu Qi, Zhaoyang Wang, Mengxin Guo, Yikai Fan, Simon X. Yang, Qifeng Li, Weihong Ma

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

AI总结 针对商业猪舍中猪只点云分割的边界模糊等问题，采用Octree Transformer骨干网络，结合软距离边界伪标签与双向跨边界语义模块，提升分割性能，为精准畜牧养殖提供可靠输入。

Comments 24 pages,9 figures, 5 tables

Sign Language Recognition Using Original and Synthetic Depth Image Based Point Cloud Data Models

基于原始和合成深度图像的点云数据模型的手语识别

Rustem Ozakar, Eyup Gedikli

机构 * Erzurum Technical University（埃尔祖鲁姆技术大学） ； Trabzon University（特拉布宗大学） 纠错

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

AI总结 该研究利用Depth Anything V2生成合成深度图像，结合三个手语数据集，采用PointNet等模型对比原始与合成深度图像点云的手语识别性能，发现多数模型中原始数据性能更优，部分模型合成数据更优。

Damage Classification for 3D Point Cloud Data via 3D Data Analysis and Vision Foundation Model-based 2D Projections

基于三维数据分析与视觉基础模型二维投影的三维点云数据损伤分类

Evan Perez, Kalelo Dukuray, Erika Ardiles-Cruz, Jie Wei

机构 * City College of New York（纽约城市学院） ； Air Force Research Lab（空军研究实验室） 纠错

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

AI总结 本研究针对三维点云损伤分类的挑战，提出3PDA与2PDA两种算法，2PDA准确率略低但计算成本大幅降低且泛化性更强，为相关任务提供了高效替代方案。

SUMI: Scalable Unified Model for 3D Point Cloud Inference

SUMI：用于三维点云推理的可扩展统一模型

Yanlong LI, Kanchana Thilakarathna

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

AI总结 针对点云补全由粗到精范式中局部细节重构不足的问题，提出扩散增强细化模块SUMI，可集成到现有模型，在多个基准数据集上实现性能提升。

PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectification

PointCHR：通过曲率感知双曲整流进行点云分析

Xinxing Yu, Liying Yang, Hao Mo, Hui Ma, Fang Kai, Ajian Liu, Yanyan Liang

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

AI总结 针对三维点云中高曲率区域难以解析的问题，提出PointCHR方法，利用双曲流形指数体积膨胀特性，通过曲率引导径向整流机制，有效缓解表示拥挤问题，提升主干网络捕捉细节能力，在多基准测试中达最优性能。

Journal ref Proceedings of the 43 rd International Conference on Machine Learning,2026

Synthetic LiDAR Data Generation and Deterministic Downsampling for Point Cloud Classification on the Edge

面向边缘设备点云分类的合成激光雷达数据生成与确定性下采样

Niclas Meyer, Stefan Reitmann

机构 * Chemnitz University of Technology（开姆尼茨工业大学） 纠错

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

AI总结 本文针对三维深度学习框架在边缘设备部署的瓶颈，提出适配树莓派5的硬件受限工作流，通过合成LiDAR数据集和特征驱动的CPL层，实现边缘端50 FPS推理与88.36%分类准确率，验证了边缘实时三维感知的可行性。

CloudDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domain

PointDiffusion: 点云领域的基于扩散的场景补全

Chidera Agbasiere, Mikhail Sannikov, Faith Ogunwoye, Erik Shaikhiev, Alex Kozinov, Ilya Mikhalchuk, Iana Zhura, Dzmitry Tsetserukou

机构 * Intelligent Space Robotics Laboratory, Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院智能空间机器人实验室） 纠错

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

AI总结 提出多令牌高斯VAE和锚点ICP地面真值精化，实现单步扩散场景补全，在SemanticKITTI上平方倒角距离降低16倍，推理延迟降低25-143倍。

PathCover: A Fast Convex Decomposition along a Path via Randomized Iterative Space Partitioning (RISP) on Point Clouds

PathCover：基于点云的随机迭代空间划分（RISP）沿路径的快速凸分解

Kunal S. Narkhede, Abhijeet M. Kulkarni, Guoquan Huang, Ioannis Poulakakis

机构 * University of Delaware（特拉华大学） ； Athena Research Center（雅典娜研究中心） ； National Technical University of Athens（雅典国家技术大学） ； HERON–Center of Excellence in Robotics（赫伦机器人卓越中心） 纠错

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

AI总结 PathCover是基于点云的快速凸分解框架，采用RISP算法，可高效生成无障碍物多面体，速度较现有方法提升一个数量级，经仿真与实机验证适用于机器人导航。

Comments 13 pages, 5 figures

Hierarchical Flow Matching for 3D Point Cloud Generation

用于三维点云生成的分层流匹配

Linhao Wang, Qichang Zhang, Ye Su, Hao Wang

机构 * Shandong Normal University（山东师范大学） ； University of Macau（澳门大学） 纠错

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

AI总结 针对现有三维点云生成方法的缺陷，提出分层流匹配（HFM），将流匹配扩展为双级结构，在ShapeNet等基准上实现了有竞争力的生成性能。

An Enhanced Geometric-Spectral Feature Learning Framework for Airborne Multispectral Point Cloud Classification

一种增强的几何-光谱特征学习框架用于机载多光谱点云分类

Xian Li, Yanfeng, Gu Linghua Xu, Aleksandra Pižurica

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

AI总结 针对机载多光谱点云高维异构、样本不平衡和类间光谱相似问题，提出基于注意力的双流特征融合框架，结合残差注意力融合块和联合损失函数，实现高精度地物分类。

Comments Revised V1