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

Divergence and Curl01:15

Divergence and Curl

1.9K
The divergence of a vector field at a point is the net outward flow of the flux out of a small volume through a closed surface enclosing the volume, as the volume tends to zero. More practically, divergence measures how much a vector field spreads out or diverges from a given point. For an outgoing flux, conventionally, the divergence is positive. The diverging point is often called the "source" of the field. Meanwhile, the negative divergence of a vector field at a point means that the...
1.9K

You might also read

Related Articles

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

Sort by
Same author

Predicting the Progression of Mild Cognitive Impairment to Alzheimer's Dementia Using Recurrent Neural Networks With a Series of Neuropsychological Tests.

Journal of clinical neurology (Seoul, Korea)·2024
Same author

Measurement Noise Recommendation for Efficient Kalman Filtering over a Large Amount of Sensor Data.

Sensors (Basel, Switzerland)·2019
Same author

Electroconvulsive therapy for major depressive disorder in a patient with a permanent skull defect: a case report.

Asia-Pacific psychiatry : official journal of the Pacific Rim College of Psychiatrists·2014
See all related articles

Related Experiment Video

Updated: Aug 29, 2025

Scalable Nanohelices for Predictive Studies and Enhanced 3D Visualization
08:03

Scalable Nanohelices for Predictive Studies and Enhanced 3D Visualization

Published on: November 12, 2014

10.6K

Anisotropic SpiralNet for 3D Shape Completion and Denoising.

Seong Uk Kim1, Jihyun Roh1, Hyeonseung Im1

  • 1Department of Computer Science and Engineering, Interdisciplinary Graduate Program in Medical Bigdata Convergence, Kangwon National University, Chuncheon 24341, Korea.

Sensors (Basel, Switzerland)
|September 9, 2022
PubMed
Summary

This study introduces a new deep learning system for 3D mesh processing. It effectively completes and denoises 3D meshes, preserving details and improving accuracy over existing methods.

Keywords:
deep learninggraph convolutional networksshape completionshape denoising

More Related Videos

Author Spotlight: Optimizing Dendritic Spine Analysis for Balanced Manual and Automated Assessment in the Hippocampus CA1 Apical Dendrites
07:45

Author Spotlight: Optimizing Dendritic Spine Analysis for Balanced Manual and Automated Assessment in the Hippocampus CA1 Apical Dendrites

Published on: September 27, 2024

2.3K
Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.2K

Related Experiment Videos

Last Updated: Aug 29, 2025

Scalable Nanohelices for Predictive Studies and Enhanced 3D Visualization
08:03

Scalable Nanohelices for Predictive Studies and Enhanced 3D Visualization

Published on: November 12, 2014

10.6K
Author Spotlight: Optimizing Dendritic Spine Analysis for Balanced Manual and Automated Assessment in the Hippocampus CA1 Apical Dendrites
07:45

Author Spotlight: Optimizing Dendritic Spine Analysis for Balanced Manual and Automated Assessment in the Hippocampus CA1 Apical Dendrites

Published on: September 27, 2024

2.3K
Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.2K

Area of Science:

  • Computer Graphics
  • Artificial Intelligence
  • 3D Reconstruction

Background:

  • 3D mesh data often suffers from noise and holes due to hardware limitations and poor capture environments.
  • Existing 3D mesh post-processing methods can introduce artifacts and lose crucial original details.
  • Effective correction of 3D mesh imperfections is vital for preserving shape and detail.

Purpose of the Study:

  • To develop a novel deep learning framework for 3D mesh completion and denoising.
  • To reconstruct high-quality 3D mesh structures from noisy and incomplete input data.
  • To address limitations of current methods in artifact removal and detail preservation.

Main Methods:

  • A novel 3D mesh completion and denoising system utilizing a deep learning framework.
  • Building upon the SpiralNet architecture with a variational deep autoencoder.
  • Employing anisotropic filters for vertex-specific convolutional filtering.

Main Results:

  • The proposed method successfully reconstructs high-quality 3D mesh structures.
  • Enhanced reconstruction quality and improved accuracy compared to previous neural network systems.
  • Effective correction of holes and various types of noise while preserving original details.

Conclusions:

  • The developed deep learning system offers a significant advancement in 3D mesh post-processing.
  • The method provides a robust solution for denoising and completing 3D meshes.
  • This approach achieves superior accuracy and detail preservation in 3D mesh reconstruction.