Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Mar 20, 2026

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

3D Human Model Reconstruction from Sparse Uncalibrated Views.

Xiaoguang Han, Kwan-Yee K Wong, Yizhou Yu

IEEE Computer Graphics and Applications

|June 1, 2016

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

A Hormone Cell Atlas maps the human endocrine system at cellular resolution.

Science (New York, N.Y.)·2026

Same author

Effective registration-free dual-phase segmentation for pancreas and pancreatic mass via symmetrical selective feature integration.

Medical image analysis·2026

Same author

MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitization.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

NR2F2 in cancer-associated fibroblasts drives immune microenvironment remodeling and promotes lung adenocarcinoma progression.

Frontiers in immunology·2026

Same author

DeepFAN, a transformer-based model for human-artificial intelligence collaborative assessment of incidental pulmonary nodules in CT scans: a multireader, multicase trial.

Nature cancer·2026

Same author

InverseDraping: Recovering Sewing Patterns From 3D Garment Surfaces via BoxMesh Bridging.

IEEE transactions on visualization and computer graphics·2026

Same journal

Integrating Domain Knowledge into Image Generation Models for Textile Design.

IEEE computer graphics and applications·2026

Same journal

Designing Metaphoric 3D Glyph Atlases for Web-Based Information Landscapes.

IEEE computer graphics and applications·2026

Same journal

Disseminating Geometric Figures for Architecture Education and Research Through a Direct Data Stream Between CAD Software and a Web Viewer.

IEEE computer graphics and applications·2026

Same journal

Designing scFlowVis: Visual Analytics for Single-Cell RNA Sequencing Analysis.

IEEE computer graphics and applications·2026

Same journal

Graph Pattern Matching based reassembly - 3DGPM.

IEEE computer graphics and applications·2026

Same journal

Making Learning Visible: Turning Public Engagement into Evidence for Academic Learning.

IEEE computer graphics and applications·2026

See all related articles

This study introduces a novel two-stage algorithm for creating detailed 3D human models from few images. The nonrigid dense correspondences (NRDC) method reconstructs clothing accurately without initial matching, using fewer images than prior techniques.

Area of Science:

Computer Vision
3D Reconstruction
Computer Graphics

Background:

Reconstructing 3D human models from images is challenging, especially with regular clothing.
Existing methods often require numerous calibrated cameras and complex initial matching steps.

Purpose of the Study:

To develop a robust algorithm for high-quality 3D human model reconstruction.
To reduce the number of required images and eliminate the need for initial sparse matching.

Main Methods:

A two-stage algorithm utilizing nonrigid dense correspondences (NRDC).
The NRDC approach establishes dense correspondences without relying on initial sparse matching.
The technique is designed to work with sparse, uncalibrated camera inputs.

More Related Videos

Construction of a Realistic, Whole-Body, Three-Dimensional Equine Skeletal Model using Computed Tomography Data

Construction of a Realistic, Whole-Body, Three-Dimensional Equine Skeletal Model using Computed Tomography Data

Published on: February 25, 2021

Author Spotlight: Advancing Human Cardiac Anatomy Through Multi-Scale Analysis of Hearts

Author Spotlight: Advancing Human Cardiac Anatomy Through Multi-Scale Analysis of Hearts

Published on: June 28, 2024

Related Experiment Videos

Last Updated: Mar 20, 2026

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Construction of a Realistic, Whole-Body, Three-Dimensional Equine Skeletal Model using Computed Tomography Data

Construction of a Realistic, Whole-Body, Three-Dimensional Equine Skeletal Model using Computed Tomography Data

Published on: February 25, 2021

Author Spotlight: Advancing Human Cardiac Anatomy Through Multi-Scale Analysis of Hearts

Author Spotlight: Advancing Human Cardiac Anatomy Through Multi-Scale Analysis of Hearts

Published on: June 28, 2024

Main Results:

Successfully reconstructed high-quality 3D models of humans in regular clothing.
Demonstrated reduced image requirements compared to previous 3D reconstruction methods.
Validated the algorithm using both existing datasets and cell phone imagery.

Conclusions:

The proposed NRDC-based algorithm offers an efficient and effective solution for 3D human body modeling.
This technique advances the field by enabling detailed reconstruction from minimal, uncalibrated image data.
The method's flexibility with different image sources, including mobile devices, broadens its applicability.