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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Isoprene-Emitting Transgenic Tobacco Shapes Root Microbiome and Enhances Growth of Co-Cultivated Non-Emitting Plants.

Plant, cell & environment·2026
Same author

Artificial Intelligence-Mediated Discharge Document for Accessible Health Care (AIM-HEALTH): Protocol for a Prospective, Observational, Noninterventional Study.

JMIR research protocols·2026
Same author

Environmental regulation of root growth angle in cereal crops.

Plant and soil·2026
Same author

Management of femoral large-bore access and closure during microaxial flow pump-supported interventions.

Frontiers in cardiovascular medicine·2026
Same author

Is thirst the missing physiological link between SGLT2 inhibitors and reduced nephrolithiasis risk?

Clinical kidney journal·2026
Same author

Discordance between mendelian randomization and randomized trials in nephrolithiasis: a multifactorial interpretation including pharmacogenetics.

Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association·2026

Related Experiment Video

Updated: Oct 15, 2025

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

286

DenseMatch: a dataset for real-time 3D reconstruction.

Marco Lombardi1, Mattia Savardi1, Alberto Signoroni1

  • 1Information Engineering Department, University of Brescia - Via Branze 38, Brescia 25123, Italy.

Data in Brief
|October 29, 2021
PubMed
Summary

A new database offers 3140 3D point clouds for quantitative analysis of 3D reconstruction and alignment. This high-resolution dataset aids in developing automated 3D scene reconstruction models.

Keywords:
3D registrationBenchmark datasetPoint-basedReal-time 3D reconstruction

More Related Videos

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

13.0K
High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques
11:34

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

Published on: December 3, 2013

15.8K

Related Experiment Videos

Last Updated: Oct 15, 2025

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

286
A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

13.0K
High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques
11:34

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

Published on: December 3, 2013

15.8K

Area of Science:

  • Computer Vision
  • 3D Imaging
  • Robotics

Background:

  • Accurate 3D reconstruction and alignment are crucial for various applications.
  • Existing datasets may lack sufficient resolution or scale for robust model development.
  • Quantitative benchmarking of 3D methods requires comprehensive and diverse data.

Purpose of the Study:

  • To introduce a novel, large-scale dataset for 3D reconstruction and alignment.
  • To facilitate real-time quantitative analysis of 3D reconstruction algorithms.
  • To support the development of advanced alignment strategies for optical scanner data.

Main Methods:

  • Acquisition of 10 subjects/objects using a high-resolution 3D scanner.
  • Generation of depth maps yielding point clouds with over 500,000 points on average.
  • Creation of a database comprising 3140 point clouds.

Main Results:

  • A comprehensive dataset suitable for quantitative evaluation.
  • Data enabling the development of new 3D reconstruction models.
  • Resources for benchmarking alignment strategies.

Conclusions:

  • The dataset provides a valuable resource for advancing 3D reconstruction and alignment research.
  • It supports the creation of automated 3D scene reconstruction from optical scanner data.
  • Facilitates rigorous benchmarking of 3D analysis techniques.