skip to main content
10.1145/3627341.3627342acmotherconferencesArticle/Chapter ViewAbstractPublication PagesiccvitConference Proceedingsconference-collections
research-article

Fitting Two Point Sets with Soft Dissimilarity

Published: 15 December 2023 Publication History

Abstract

Estimating transformation parameters between 3D point sets is crucial for various motion-based 3D vision tasks, such as point cloud registration, pose estimation, 3D object recognition, and tracking. Traditional methods rely on optimizing parameters from a subset of physical point pairs with hard correspondences. However, these approaches face challenges in complex scenes with sparse or partially overlapping point sets, lacking sufficient corresponding points. In this paper, we propose a novel transformation estimation approach based on soft dissimilarity, a metric that quantifies point-to-point correlation using spatial distance. Our method leverages soft dissimilarity to obtain ample corresponding point pairs for each raw point, improving the estimation process. Extensive experiments demonstrate that our method achieves superior accuracy and robustness compared to traditional correspondence-based transformation estimation methods across various scenarios.

References

[1]
Sheng Ao, Qingyong Hu, Bo Yang, Andrew Markham, and Yulan Guo. 2021. Spinnet: Learning a general surface descriptor for 3d point cloud registration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 11753–11762.
[2]
K Somani Arun, Thomas S Huang, and Steven D Blostein. 1987. Least-squares fitting of two 3-D point sets. IEEE Transactions on pattern analysis and machine intelligence5 (1987), 698–700.
[3]
Simon Baker and Iain Matthews. 2004. Lucas-kanade 20 years on: A unifying framework. International journal of computer vision 56 (2004), 221–255.
[4]
Paul J Besl and Neil D McKay. 1992. Method for registration of 3-D shapes. In Sensor fusion IV: control paradigms and data structures, Vol. 1611. Spie, 586–606.
[5]
Seth D Billings, Emad M Boctor, and Russell H Taylor. 2015. Iterative most-likely point registration (IMLP): A robust algorithm for computing optimal shape alignment. PloS one 10, 3 (2015), e0117688.
[6]
Sungjoon Choi, Qian-Yi Zhou, and Vladlen Koltun. 2015. Robust reconstruction of indoor scenes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5556–5565.
[7]
Christopher Choy, Wei Dong, and Vladlen Koltun. 2020. Deep global registration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2514–2523.
[8]
Christopher Choy, Jaesik Park, and Vladlen Koltun. 2019. Fully convolutional geometric features. In Proceedings of the IEEE/CVF international conference on computer vision. 8958–8966.
[9]
David W Eggert, Adele Lorusso, and Robert B Fisher. 1997. Estimating 3-D rigid body transformations: a comparison of four major algorithms. Machine vision and applications 9, 5-6 (1997), 272–290.
[10]
Olivier D Faugeras and Martial Hebert. 1983. A 3-D recognition and positioning algorithm using geometrical matching between primitive surfaces. In Proceedings of the Eighth international joint conference on Artificial intelligence-Volume 2. 996–1002.
[11]
Berthold KP Horn. 1987. Closed-form solution of absolute orientation using unit quaternions. Josa a 4, 4 (1987), 629–642.
[12]
Berthold KP Horn, Hugh M Hilden, and Shahriar Negahdaripour. 1988. Closed-form solution of absolute orientation using orthonormal matrices. JOSA A 5, 7 (1988), 1127–1135.
[13]
Shengyu Huang, Zan Gojcic, Mikhail Usvyatsov, Andreas Wieser, and Konrad Schindler. 2021. Predator: Registration of 3D Point Clouds With Low Overlap. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 4267–4276.
[14]
Shengyu Huang, Zan Gojcic, Mikhail Usvyatsov, Andreas Wieser, and Konrad Schindler. 2021. Predator: Registration of 3d point clouds with low overlap. In Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition. 4267–4276.
[15]
TS Huang, SD Blostein, and EA Margerum. 1986. Least-squares estimation of motion parameters from 3-D point correspondences. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, Vol. 10. IEEE Computer Soc. Press Washington DC, 112–115.
[16]
Zheng Qin, Hao Yu, Changjian Wang, Yulan Guo, Yuxing Peng, and Kai Xu. 2022. Geometric transformer for fast and robust point cloud registration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11143–11152.
[17]
Szymon Rusinkiewicz and Marc Levoy. 2001. Efficient variants of the ICP algorithm. In Proceedings third international conference on 3-D digital imaging and modeling. IEEE, 145–152.
[18]
Michael W Walker, Lejun Shao, and Richard A Volz. 1991. Estimating 3-D location parameters using dual number quaternions. CVGIP: image understanding 54, 3 (1991), 358–367.
[19]
Hao Yu, Fu Li, Mahdi Saleh, Benjamin Busam, and Slobodan Ilic. 2021. Cofinet: Reliable coarse-to-fine correspondences for robust pointcloud registration. Advances in Neural Information Processing Systems 34 (2021), 23872–23884.
[20]
Andy Zeng, Shuran Song, Matthias Nießner, Matthew Fisher, Jianxiong Xiao, and Thomas Funkhouser. 2017. 3dmatch: Learning local geometric descriptors from rgb-d reconstructions. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1802–1811.

Index Terms

  1. Fitting Two Point Sets with Soft Dissimilarity

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICCVIT '23: Proceedings of the 2023 International Conference on Computer, Vision and Intelligent Technology
    August 2023
    378 pages
    ISBN:9798400708701
    DOI:10.1145/3627341
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 15 December 2023

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. 3D point sets
    2. Soft dissimilarity
    3. Transformation estimation

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    ICCVIT 2023

    Acceptance Rates

    ICCVIT '23 Paper Acceptance Rate 54 of 142 submissions, 38%;
    Overall Acceptance Rate 54 of 142 submissions, 38%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 9
      Total Downloads
    • Downloads (Last 12 months)8
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 20 Jan 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media