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: Jul 7, 2026

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Silhouette-based 3-D model reconstruction from multiple images.

A Y Mulayim¹, U Yilmaz, V Atalay

¹Dept. of Comput. Eng., Middle East Tech. Univ., Ankara, Turkey.

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society

|February 2, 2008

Summary

This study details a complete system for 3-D model reconstruction using silhouette-based methods. It introduces novel algorithms for object bounding and photoconsistency, improving 3-D graphical model accuracy.

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

[Postoperative imaging following spinal surgery for traumatic injuries].

Radiologie (Heidelberg, Germany)·2025

Same author

Effects of glucagon as a neurohormone on the central nervous system and glucose homeostasis.

European review for medical and pharmacological sciences·2024

Same author

[COVID-19: neurological manifestations-update : What we know so far].

Der Radiologe·2021

Same author

A new and reliable landmark in parotid surgery: tragomastoid groove (Akil Groove).

European review for medical and pharmacological sciences·2021

Same author

[Nonaccidental traumatic brain injury in infants and children].

Der Radiologe·2021

Same author

[Spontaneous craniocervical dissection].

Der Radiologe·2021

Area of Science:

Computer Vision
3D Reconstruction
Geometric Modeling

Background:

Silhouette-based reconstruction is a known technique for creating 3D models.
Existing methods often have limitations in robustness and threshold selection.

Purpose of the Study:

To present a complete, end-to-end system for 3D graphical model reconstruction.
To improve upon existing silhouette-based reconstruction methods.

Main Methods:

Developed a multi-image calibration method to extract the rotation axis of a turntable.
Created an algorithm for robust estimation of the object's initial bounding volume.
Implemented a photoconsistency algorithm to overcome silhouette-based reconstruction disadvantages, featuring simplified visibility checks and no threshold selection.

More Related Videos

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

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

Published on: September 28, 2019

Related Experiment Videos

Last Updated: Jul 7, 2026

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

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

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

Published on: September 28, 2019

Main Results:

Demonstrated a functional, detailed end-to-end system for 3D reconstruction.
Successfully reconstructed both real-world and synthetic objects.
Achieved improved accuracy and robustness compared to traditional methods.

Conclusions:

The presented system offers a comprehensive solution for 3D model reconstruction.
The novel algorithms enhance the reliability and efficiency of silhouette-based reconstruction.
The approach is effective for generating accurate 3D graphical models.