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 Video

Updated: Nov 7, 2025

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
10:23

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

3.3K

An Efficient 3D Human Pose Retrieval and Reconstruction from 2D Image-Based Landmarks.

Hashim Yasin1, Björn Krüger2

  • 1School of Computing, National University of Computer and Emerging Sciences, Islamabad 44000, Pakistan.

Sensors (Basel, Switzerland)
|April 30, 2021
PubMed
Summary
This summary is machine-generated.

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

Assessing the Impact of Virtual Reality, Augmented Reality, and Video Games on Improving Post-Traumatic Stress Disorder Symptoms: A Systematic Review and Meta-Analysis.

Inquiry : a journal of medical care organization, provision and financing·2026
Same author

EPIStress: A multimodal dataset of Physiological signals to measure cognitive stress in epilepsy patients.

Scientific data·2025
Same author

Eyes on cognition: Exploring oculomotor correlates of cognitive function in patients with epilepsy.

Epilepsy & behavior : E&B·2025
Same author

The Newer, the More Secure? Standards-Compliant Bluetooth Low Energy Man-in-the-Middle Attacks on Fitness Trackers.

Sensors (Basel, Switzerland)·2025
Same author

Chitin Analysis in Insect-Based Feed Ingredients and Mixed Feed: Development of a Cost-Effective and Practical Method.

Journal of animal physiology and animal nutrition·2025
Same author

Generisch-Net: A Generic Deep Model for Analyzing Human Motion with Wearable Sensors in the Internet of Health Things.

Sensors (Basel, Switzerland)·2024

This study presents a novel framework for 3D human pose reconstruction from 2D landmarks. The method efficiently retrieves and reconstructs 3D poses from diverse 2D inputs, including sketches.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Human Pose Estimation

Background:

  • Accurate 3D human pose estimation from 2D images is challenging due to depth ambiguity.
  • Existing methods often struggle with diverse input modalities like sketches or in-the-wild images.

Purpose of the Study:

  • To develop an efficient and novel architecture for 3D articulated human pose retrieval and reconstruction.
  • To enable accurate 3D pose inference from various 2D inputs, including synthetic data, real images, and hand-drawn sketches.

Main Methods:

  • A data-driven framework normalizing 3D Motion Capture (MoCap) poses to create a 2D pose knowledge base using virtual cameras.
  • A retrieval mechanism identifying similar MoCap poses based on 2D joint features.
  • A reconstruction process utilizing retrieved poses and a weak perspective camera model to minimize error, including a nonlinear method for camera parameter estimation.
Keywords:
3D articulated pose estimation3D human pose retrievalfeature setsknowledge-basemotion captureoptimization

More Related Videos

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

404
Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.2K

Related Experiment Videos

Last Updated: Nov 7, 2025

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
10:23

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

3.3K
Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

404
Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.2K

Main Results:

  • The architecture successfully retrieves and reconstructs 3D human poses from diverse 2D inputs.
  • Evaluations on synthetic, ground-truth, in-the-wild images, and sketches demonstrate robust performance.
  • Quantitative studies on the PARSE dataset show competitive results compared to state-of-the-art methods.

Conclusions:

  • The proposed method offers an efficient and effective solution for 3D human pose retrieval and reconstruction.
  • The framework's ability to handle various 2D inputs, including challenging cases like sketches, highlights its versatility.
  • The system achieves state-of-the-art performance, advancing the field of 3D human pose estimation.