3D 视觉 - arXivDaily 专题

1804.02085 2018-04-09 cs.CV cs.RO 62%

Performance Evaluation of 3D Correspondence Grouping Algorithms

Jiaqi Yang, Ke Xian, Yang Xiao, Zhiguo Cao

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

Comments Accepted to 3DV 2017, (Spotlight)

1703.01661 2018-03-13 cs.RO cs.CV 62%

SegICP: Integrated Deep Semantic Segmentation and Pose Estimation

Jay M. Wong, Vincent Kee, Tiffany Le, Syler Wagner, Gian-Luca Mariottini, Abraham Schneider, Lei Hamilton, Rahul Chipalkatty, Mitchell Hebert, David M. S. Johnson, Jimmy Wu, Bolei Zhou, Antonio Torralba

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

Comments IROS camera-ready

1712.08409 2018-01-31 cs.RO cs.CV 62%

Detection and Tracking of General Movable Objects in Large 3D Maps

Nils Bore, Johan Ekekrantz, Patric Jensfelt, John Folkesson

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

Comments Submitted for peer review

1711.05864 2017-11-17 cs.CV cs.RO 62%

Hidden Markov Random Field Iterative Closest Point

John Stechschulte, Christoffer Heckman

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

1708.05514 2017-08-21 cs.CV cs.RO 62%

Reflectance Intensity Assisted Automatic and Accurate Extrinsic Calibration of 3D LiDAR and Panoramic Camera Using a Printed Chessboard

Weimin Wang, Ken Sakurada, Nobuo Kawaguchi

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

Comments 20 pages, submitted to the journal of Remote Sensing

Journal ref Remote Sensing, 9(8):851 (2017)

1609.03947 2017-07-27 cs.CV cs.RO 62%

Associating Grasp Configurations with Hierarchical Features in Convolutional Neural Networks

Li Yang Ku, Erik Learned-Miller, Rod Grupen

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

Comments 8 pages, 9 figures, IROS 2017

1706.05340 2017-06-19 cs.RO cs.CV 62%

Robotic Ironing with 3D Perception and Force/Torque Feedback in Household Environments

David Estevez, Juan G. Victores, Raul Fernandez-Fernandez, Carlos Balaguer

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

Comments Accepted and to be published on the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017) that will be held in Vancouver, Canada, September 24-28, 2017

1705.09785 2017-05-30 cs.RO cs.CV 62%

LiDAR-Camera Calibration using 3D-3D Point correspondences

Ankit Dhall, Kunal Chelani, Vishnu Radhakrishnan, K. M. Krishna

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

1606.02378 2017-04-03 cs.LG cs.AI cs.CV cs.RO 62%

SE3-Nets: Learning Rigid Body Motion using Deep Neural Networks

Arunkumar Byravan, Dieter Fox

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

Comments 8 pages. To appear at the IEEE International Conference on Robotics and Automation (ICRA), 2017. V2 Update: Final version submitted to ICRA with experiments testing the robustness of the system to noise and preliminary results on real world data

1703.04665 2017-03-16 cs.RO cs.CV 62%

Geometry-Based Region Proposals for Real-Time Robot Detection of Tabletop Objects

Alexander Broad, Brenna Argall

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

Comments Update based on work presented at RSS 2016 Deep Learning Workshop

1603.02617 2017-01-10 cs.CV cs.RO 62%

Iterative Hough Forest with Histogram of Control Points for 6 DoF Object Registration from Depth Images

Caner Sahin, Rigas Kouskouridas, Tae-Kyun Kim

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

Comments IROS 2016

1610.01326 2016-10-06 cs.RO cs.CV 62%

Mobility Map Computations for Autonomous Navigation using an RGBD Sensor

Nicolò Genesio, Tariq Abuhashim, Fabio Solari, Manuela Chessa, Lorenzo Natale

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

1609.07826 2016-09-27 cs.CV cs.RO 62%

Multiview RGB-D Dataset for Object Instance Detection

Georgios Georgakis, Md Alimoor Reza, Arsalan Mousavian, Phi-Hung Le, Jana Kosecka

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

1412.1219 2014-12-04 cs.RO cs.CV 62%

Colorisation et texturation temps réel d'environnements urbains par système mobile avec scanner laser et caméra fish-eye

Jean-Emmanuel Deschaud, Xavier Brun, François Goulette

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

Comments in French

Journal ref Revue Francaise de Photogrammetrie et de Teledetection, Revue Francaise de Photogrammetrie et de Teledetection, 2010, pp.29-37

1404.5765 2014-04-24 cs.CV cs.RO 62%

Find my mug: Efficient object search with a mobile robot using semantic segmentation

Daniel Wolf, Markus Bajones, Johann Prankl, Markus Vincze

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

Comments Part of the OAGM 2014 proceedings (arXiv:1404.3538)

1311.7295 2013-12-02 cs.RO cs.CV 62%

Glasgow's Stereo Image Database of Garments

Gerardo Aragon-Camarasa, Susanne B. Oehler, Yuan Liu, Sun Li, Paul Cockshott, J. Paul Siebert

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

Comments 7 pages, 6 figure, image database

1212.6837 2013-01-01 cs.RO cs.AI cs.CV 62%

Autonomously Learning to Visually Detect Where Manipulation Will Succeed

Hai Nguyen, Charles C. Kemp

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

Comments 15 pages, 10 figures. Submitted to the Autonomous Robots Journal Special Issue "Beyond Grasping - Modern Approaches for Dexterous Manipulation"

1106.4632 2011-06-24 cs.RO cs.AI cs.CV 62%

Inferring 3D Articulated Models for Box Packaging Robot

Heran Yang, Tiffany Low, Matthew Cong, Ashutosh Saxena

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

Comments For: RSS 2011 Workshop on Mobile Manipulation: Learning to Manipulate

2603.03892 2026-07-16 cs.CV cs.AI 版本更新 61%

A novel network for classification of cuneiform tablet metadata

一种用于楔形文字泥板元数据分类的新型网络

Frederik Hagelskjær

机构 * SDU Robotics, University of Southern Denmark（丹麦南部大学机器人研究所）

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

AI总结本文提出了一种新型网络，通过缩小点云并整合局部和全局信息，有效提升楔形文字泥板元数据分类性能。

Comments Point cloud, deep learning, cuneiform

2606.18429 2026-06-23 cs.CV cs.AI cs.LG 新提交 61%

CAOA -- Completion-Assisted Object-CAD Alignment

CAOA -- 补全辅助的物体-CAD对齐

Hiranya Garbha Kumar, Minhas Kamal, Balakrishnan Prabhakaran

机构 * University at Albany（奥尔巴尼大学）

专题命中点云：point cloud(abstract)；分类 cs.CV；3D vision(journal_ref)

AI总结提出CAOA方法，结合语义感知点云补全和对称感知相对位姿估计，在Scan2CAD上实现17%精度提升，并发布S2C-Completion数据集。

Comments GitHub: https://github.com/MinhasKamal/CAOA

Journal ref Thirteenth International Conference on 3D Vision (3DV), 2026

2606.11578 2026-06-11 cs.CV 新提交 61%

Contactless 3D Human Body Measurement Using Depth Cameras for Smart Health Monitoring

基于深度相机的非接触式3D人体测量用于智能健康监测

Martha Asare, Xuan Wang, Juan Lopez Alvarenga, Lois Akosua Serwaa, Jinghao Yang

机构 * Department of Computer（计算机系）； Department of Information（信息系）； Department of Human Genetics（人类遗传学系）； University of Texas Rio Grande Valley（德克萨斯大学里奥格兰德谷分校）； Department of Electrical and Computer Engineering（电气与计算机工程系）

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

AI总结提出一种基于深度相机和3D点云的非接触式人体测量框架，通过空间滤波、地标选择及体素/网格分析实现身高、臂展、体积和表面积等关键指标的准确估计。

Comments 6 pages, 4 figures. Depth camera-based framework for contactless anthropometric measurement and geometric analysis using 3D point clouds

2606.10594 2026-06-10 cs.CV 新提交 61%

Segment and Select: Vision-Language Segmentation in 3D Scenarios

Segment and Select: 3D场景中的视觉-语言分割

Yulin Chen, Zhihang Zhong, Yuenan Hou

机构 * Shanghai AI Laboratory（上海人工智能实验室）； University of Science and Technology of China（中国科学技术大学）； Shanghai Jiaotong University（上海交通大学）

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

AI总结提出SEGA3D范式，通过掩码候选生成器、大语言模型和语义空间选择器实现3D场景中基于语言指令的细粒度分割，在ScanNet和Matterport3D上分别提升8.3和5.3 mIoU。

Comments The core idea is to reformulate 3D vision-language segmentation as the segment-and-select paradigm (free from the superpoint dependency)

2602.04343 2026-06-02 cs.CV 61%

Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perception

寻找NeMO：面向少样本感知的模板视图几何感知表示

Sebastian Jung, Leonard Klüpfel, Rudolph Triebel, Maximilian Durner

机构 * German Aerospace Center (DLR)（德国航空航天中心（DLR））

专题命中点云：point cloud(abstract)；分类 cs.CV；3D vision(journal_ref)

AI总结提出NeMO（神经记忆对象）表示，通过少量RGB模板视图编码生成稀疏点云，实现未见对象的检测、分割和6DoF姿态估计，无需重训练。

Comments 17 pages including supplement, published in 3DV 2026, Project website: https://sebastian-jung.github.io/nemo/

Journal ref Proceedings of the International Conference on 3D Vision (3DV), 2026

2311.14262 2025-02-24 cs.CV 61%

ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation

Yuheng Xue, Nenglun Chen, Jun Liu, Wenyun Sun

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

Comments 2025 International Conference on 3D Vision (3DV)

2310.11284 2023-10-18 cs.CV 61%

Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior

Ruibo Li, Chi Zhang, Zhe Wang, Chunhua Shen, Guosheng Lin

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

Comments An extension of our CVPR 2022 paper (RigidFlow: Self-Supervised Scene Flow Learning on Point Clouds by Local Rigidity Prior)

2302.02125 2023-04-26 eess.IV cs.CV cs.LG 61%

Weakly-Supervised 3D Medical Image Segmentation using Geometric Prior and Contrastive Similarity

Hao Du, Qihua Dong, Yan Xu, Jing Liao

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

Comments Weakly-supervised Segmentation, Medical Image Segmentation, Contrastive Similarity, Geometric Prior, Point Cloud

Journal ref IEEE Trans. Med. Imaging, Early Access, pp. 1-1, April 24, 2023

2204.08084 2022-04-28 cs.CV 61%

Learning 3D Semantics from Pose-Noisy 2D Images with Hierarchical Full Attention Network

Yuhang He, Lin Chen, Junkun Xie, Long Chen

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

Comments 3D Point Cloud Semantic Segmentation, Semantic Aggregation from Images, Pose Noise

2103.02263 2021-03-04 cs.CV 61%

LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment

Fabian Duerr, Mario Pfaller, Hendrik Weigel, Juergen Beyerer

专题命中点云：point cloud(abstract)；分类 cs.CV；3D vision(journal_ref)

Journal ref International Conference on 3D Vision (3DV), pages 781-790, 2020

2010.09185 2020-10-20 cs.CV cs.AI 61%

MaskNet: A Fully-Convolutional Network to Estimate Inlier Points

Vinit Sarode, Animesh Dhagat, Rangaprasad Arun Srivatsan, Nicolas Zevallos, Simon Lucey, Howie Choset

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

Comments Accepted at International Conference on 3D Vision (3DV, 2020)

1908.03851 2019-08-13 cs.CV 61%

IoU Loss for 2D/3D Object Detection

Dingfu Zhou, Jin Fang, Xibin Song, Chenye Guan, Junbo Yin, Yuchao Dai, Ruigang Yang

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

Comments Accepted by international conference on 3d vision 2019

1. 点云 7719 篇

Performance Evaluation of 3D Correspondence Grouping Algorithms

SegICP: Integrated Deep Semantic Segmentation and Pose Estimation

Detection and Tracking of General Movable Objects in Large 3D Maps

Hidden Markov Random Field Iterative Closest Point

Reflectance Intensity Assisted Automatic and Accurate Extrinsic Calibration of 3D LiDAR and Panoramic Camera Using a Printed Chessboard

Associating Grasp Configurations with Hierarchical Features in Convolutional Neural Networks

Robotic Ironing with 3D Perception and Force/Torque Feedback in Household Environments

LiDAR-Camera Calibration using 3D-3D Point correspondences

SE3-Nets: Learning Rigid Body Motion using Deep Neural Networks

Geometry-Based Region Proposals for Real-Time Robot Detection of Tabletop Objects

Iterative Hough Forest with Histogram of Control Points for 6 DoF Object Registration from Depth Images

Mobility Map Computations for Autonomous Navigation using an RGBD Sensor

Multiview RGB-D Dataset for Object Instance Detection

Colorisation et texturation temps réel d'environnements urbains par système mobile avec scanner laser et caméra fish-eye

Find my mug: Efficient object search with a mobile robot using semantic segmentation

Glasgow's Stereo Image Database of Garments

Autonomously Learning to Visually Detect Where Manipulation Will Succeed

Inferring 3D Articulated Models for Box Packaging Robot

A novel network for classification of cuneiform tablet metadata

CAOA -- Completion-Assisted Object-CAD Alignment

Contactless 3D Human Body Measurement Using Depth Cameras for Smart Health Monitoring

Segment and Select: Vision-Language Segmentation in 3D Scenarios

Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perception

ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation

Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior

Weakly-Supervised 3D Medical Image Segmentation using Geometric Prior and Contrastive Similarity

Learning 3D Semantics from Pose-Noisy 2D Images with Hierarchical Full Attention Network

LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment

MaskNet: A Fully-Convolutional Network to Estimate Inlier Points

IoU Loss for 2D/3D Object Detection