The Science and Information (SAI) Organization
  • Home
  • About Us
  • Journals
  • Conferences
  • Contact Us

Publication Links

  • IJACSA
  • Author Guidelines
  • Publication Policies
  • Digital Archiving Policy
  • Promote your Publication
  • Metadata Harvesting (OAI2)

IJACSA

  • About the Journal
  • Call for Papers
  • Editorial Board
  • Author Guidelines
  • Submit your Paper
  • Current Issue
  • Archives
  • Indexing
  • Fees/ APC
  • Reviewers
  • Apply as a Reviewer

IJARAI

  • About the Journal
  • Archives
  • Indexing & Archiving

Special Issues

  • Home
  • Archives
  • Proposals
  • Guest Editors
  • SUSAI-EE 2025
  • ICONS-BA 2025
  • IoT-BLOCK 2025

Future of Information and Communication Conference (FICC)

  • Home
  • Call for Papers
  • Submit your Paper/Poster
  • Register
  • Venue
  • Contact

Computing Conference

  • Home
  • Call for Papers
  • Submit your Paper/Poster
  • Register
  • Venue
  • Contact

Intelligent Systems Conference (IntelliSys)

  • Home
  • Call for Papers
  • Submit your Paper/Poster
  • Register
  • Venue
  • Contact

Future Technologies Conference (FTC)

  • Home
  • Call for Papers
  • Submit your Paper/Poster
  • Register
  • Venue
  • Contact
  • Home
  • Call for Papers
  • Editorial Board
  • Guidelines
  • Submit
  • Current Issue
  • Archives
  • Indexing
  • Fees
  • Reviewers
  • Subscribe

DOI: 10.14569/IJACSA.2020.0110245
PDF

Three-Dimensional Shape Reconstruction from a Single Image by Deep Learning

Author 1: Kentaro Sakai
Author 2: Yoshiaki Yasumura

International Journal of Advanced Computer Science and Applications(IJACSA), Volume 11 Issue 2, 2020.

  • Abstract and Keywords
  • How to Cite this Article
  • {} BibTeX Source

Abstract: Reconstructing a three-dimensional (3D) shape from a single image is one of the main topics in the field of computer vision. Some of the methods for 3D reconstruction adopt machine learning. These methods use machine learning for acquiring the relationship between 3D shape and 2D image, and reconstruct 3D shapes by using the learned relationship. However, since only predefined features (pixels in the image) are used, it is not possible to obtain the desired features of the 2D image for 3D reconstruction. Therefore, this paper presents a method for reconstructing 3D shapes by learning features of 2D images using deep learning. This method uses Convolutional Neural Network (CNN) for feature learning to reconstruct a 3D shape. Pooling layers and convolutional layers of the CNN capture spatial information about images and automatically select valuable image features. This paper presents two types of the reconstruction methods. The first one is to first estimate the normal vector of the object, and then reconstruct the 3D shape from the normal vector by deep learning. The second one is direct reconstruction of the 3D shape from an image by a deep neural network. The experimental results using human face images showed that the proposed method can reconstruct 3D shapes with higher accuracy than the previous methods.

Keywords: Computer vision; 3D reconstruction; deep learning; convolutional neural network; feature learning; normal vector

Kentaro Sakai and Yoshiaki Yasumura, “Three-Dimensional Shape Reconstruction from a Single Image by Deep Learning” International Journal of Advanced Computer Science and Applications(IJACSA), 11(2), 2020. http://dx.doi.org/10.14569/IJACSA.2020.0110245

@article{Sakai2020,
title = {Three-Dimensional Shape Reconstruction from a Single Image by Deep Learning},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2020.0110245},
url = {http://dx.doi.org/10.14569/IJACSA.2020.0110245},
year = {2020},
publisher = {The Science and Information Organization},
volume = {11},
number = {2},
author = {Kentaro Sakai and Yoshiaki Yasumura}
}



Copyright Statement: This is an open access article licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, even commercially as long as the original work is properly cited.

IJACSA

Upcoming Conferences

IntelliSys 2025

28-29 August 2025

  • Amsterdam, The Netherlands

Future Technologies Conference 2025

6-7 November 2025

  • Munich, Germany

Healthcare Conference 2026

21-22 May 2026

  • Amsterdam, The Netherlands

Computing Conference 2026

9-10 July 2026

  • London, United Kingdom

IntelliSys 2026

3-4 September 2026

  • Amsterdam, The Netherlands

Computer Vision Conference 2026

15-16 October 2026

  • Berlin, Germany
The Science and Information (SAI) Organization
BACK TO TOP

Computer Science Journal

  • About the Journal
  • Call for Papers
  • Submit Paper
  • Indexing

Our Conferences

  • Computing Conference
  • Intelligent Systems Conference
  • Future Technologies Conference
  • Communication Conference

Help & Support

  • Contact Us
  • About Us
  • Terms and Conditions
  • Privacy Policy

© The Science and Information (SAI) Organization Limited. All rights reserved. Registered in England and Wales. Company Number 8933205. thesai.org