Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Multiview registration of 3D scenes by minimizing error between coordinate frames.

Gregory C Sharp1, Sang W Lee, David K Wehe

  • 1Department of Radiation Oncology, Massachusetts General Hospital, Boston, MA 02114, USA. gcsharp@partners.org

IEEE Transactions on Pattern Analysis and Machine Intelligence
|January 12, 2005
PubMed
Summary

This study presents a novel method for large-scale multiview registration of range images, separating local and global registration problems. The approach efficiently distributes accumulated errors across views without needing point correspondences, improving computational efficiency.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Safety and effectiveness of the Colovac anastomosis protection device compared with diverting ileostomy after low anterior resection: protocol for an international, multicentre, prospective, non-randomised comparative study (SAFE-3).

BMJ open gastroenterology·2026
Same author

Femoral Derotational Osteotomy for Idiopathic Excessive Femoral Anteversion: A Comparison of Surgical Techniques.

Journal of pediatric orthopedics·2026
Same author

PRISM: An open-source framework for regularized material decomposition on a novel kV dual-layer imager.

Medical physics·2026
Same author

Corrigendum to "Clinical target volumes for glioma - Automated delineation to improve neuroanatomic consistency" [Phys. Imaging Radiat. Oncol. 36 (2025) 100865].

Physics and imaging in radiation oncology·2026
Same author

Real-time bowel perfusion monitoring with FUJIFILM ELUXEO® VISION endoscopic imaging system in colorectal surgery.

Surgical endoscopy·2025
Same author

Probabilistic clinical target definition with nearest neighbor correlation.

Physics in medicine and biology·2025

Area of Science:

  • Computer Vision
  • Robotics
  • Computational Geometry

Background:

  • Accurate 3D reconstruction requires aligning multiple range images (point clouds) from unknown viewpoints.
  • Traditional multiview registration methods face computational challenges with large datasets and unknown camera poses.

Purpose of the Study:

  • To develop an efficient and scalable algorithm for large-scale multiview registration of range images.
  • To decouple the local pairwise registration from the global error distribution problem.

Main Methods:

  • A graph-based optimization framework is proposed for global error distribution.
  • The view graph is decomposed into cycles, enabling closed-form solutions for transformation parameters within each cycle.
  • An iterative procedure integrates cycle solutions to globally optimize the registration.

Related Experiment Videos

Main Results:

  • The proposed method effectively distributes accumulated errors across the view graph.
  • The approach does not require explicit point correspondences between views.
  • It can integrate various pairwise registration techniques and robot odometry data.

Conclusions:

  • The presented method offers a computationally efficient solution for large-scale multiview registration.
  • This technique enhances the robustness and scalability of 3D reconstruction from range data.
  • The framework's flexibility allows integration with diverse registration algorithms.