Three-dimensional shape reconstruction from a single image based on feature learning

Kentaro Sakai, Yoshiaki Yasumura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Many previous works have proposed methods for reconstructing a three-dimensional (3D) shape from a single image. Some of the methods reconstruct a 3D shape using machine learning. These methods learn the relationship between a 3D shape and a 2D image. However, they cannot learn the desirable features of 2D images for 3D reconstruction, because they use only predefined features. Therefore, this paper presents a method for reconstructing the 3D shape by learning features of a 2D image. This method reconstructs a 3D shape by using Convolutional Neural Network (CNN) for feature learning. The pooling layer and the convolutional layer of the CNN enable us to acquire spatial information of an image and automatically select the valuable feature of the image. From the experimental results using human face images, this method can reconstruct the 3D shape with better accuracy than the previous methods.

Original languageEnglish
Title of host publication2018 International Workshop on Advanced Image Technology, IWAIT 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-4
Number of pages4
ISBN (Electronic)9781538626153
DOIs
Publication statusPublished - 2018 May 30
Event2018 International Workshop on Advanced Image Technology, IWAIT 2018 - Chiang Mai, Thailand
Duration: 2018 Jan 72018 Jan 9

Other

Other2018 International Workshop on Advanced Image Technology, IWAIT 2018
CountryThailand
CityChiang Mai
Period18/1/718/1/9

Fingerprint

Neural networks
Learning systems

Keywords

  • 3D shape reconstruction
  • Convolutional Neural Network
  • feature learning

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Media Technology

Cite this

Sakai, K., & Yasumura, Y. (2018). Three-dimensional shape reconstruction from a single image based on feature learning. In 2018 International Workshop on Advanced Image Technology, IWAIT 2018 (pp. 1-4). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IWAIT.2018.8369636

Three-dimensional shape reconstruction from a single image based on feature learning. / Sakai, Kentaro; Yasumura, Yoshiaki.

2018 International Workshop on Advanced Image Technology, IWAIT 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-4.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sakai, K & Yasumura, Y 2018, Three-dimensional shape reconstruction from a single image based on feature learning. in 2018 International Workshop on Advanced Image Technology, IWAIT 2018. Institute of Electrical and Electronics Engineers Inc., pp. 1-4, 2018 International Workshop on Advanced Image Technology, IWAIT 2018, Chiang Mai, Thailand, 18/1/7. https://doi.org/10.1109/IWAIT.2018.8369636
Sakai K, Yasumura Y. Three-dimensional shape reconstruction from a single image based on feature learning. In 2018 International Workshop on Advanced Image Technology, IWAIT 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-4 https://doi.org/10.1109/IWAIT.2018.8369636
Sakai, Kentaro ; Yasumura, Yoshiaki. / Three-dimensional shape reconstruction from a single image based on feature learning. 2018 International Workshop on Advanced Image Technology, IWAIT 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-4
@inproceedings{d6282e788c45474b8ff5a1d84d8b9e71,
title = "Three-dimensional shape reconstruction from a single image based on feature learning",
abstract = "Many previous works have proposed methods for reconstructing a three-dimensional (3D) shape from a single image. Some of the methods reconstruct a 3D shape using machine learning. These methods learn the relationship between a 3D shape and a 2D image. However, they cannot learn the desirable features of 2D images for 3D reconstruction, because they use only predefined features. Therefore, this paper presents a method for reconstructing the 3D shape by learning features of a 2D image. This method reconstructs a 3D shape by using Convolutional Neural Network (CNN) for feature learning. The pooling layer and the convolutional layer of the CNN enable us to acquire spatial information of an image and automatically select the valuable feature of the image. From the experimental results using human face images, this method can reconstruct the 3D shape with better accuracy than the previous methods.",
keywords = "3D shape reconstruction, Convolutional Neural Network, feature learning",
author = "Kentaro Sakai and Yoshiaki Yasumura",
year = "2018",
month = "5",
day = "30",
doi = "10.1109/IWAIT.2018.8369636",
language = "English",
pages = "1--4",
booktitle = "2018 International Workshop on Advanced Image Technology, IWAIT 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Three-dimensional shape reconstruction from a single image based on feature learning

AU - Sakai, Kentaro

AU - Yasumura, Yoshiaki

PY - 2018/5/30

Y1 - 2018/5/30

N2 - Many previous works have proposed methods for reconstructing a three-dimensional (3D) shape from a single image. Some of the methods reconstruct a 3D shape using machine learning. These methods learn the relationship between a 3D shape and a 2D image. However, they cannot learn the desirable features of 2D images for 3D reconstruction, because they use only predefined features. Therefore, this paper presents a method for reconstructing the 3D shape by learning features of a 2D image. This method reconstructs a 3D shape by using Convolutional Neural Network (CNN) for feature learning. The pooling layer and the convolutional layer of the CNN enable us to acquire spatial information of an image and automatically select the valuable feature of the image. From the experimental results using human face images, this method can reconstruct the 3D shape with better accuracy than the previous methods.

AB - Many previous works have proposed methods for reconstructing a three-dimensional (3D) shape from a single image. Some of the methods reconstruct a 3D shape using machine learning. These methods learn the relationship between a 3D shape and a 2D image. However, they cannot learn the desirable features of 2D images for 3D reconstruction, because they use only predefined features. Therefore, this paper presents a method for reconstructing the 3D shape by learning features of a 2D image. This method reconstructs a 3D shape by using Convolutional Neural Network (CNN) for feature learning. The pooling layer and the convolutional layer of the CNN enable us to acquire spatial information of an image and automatically select the valuable feature of the image. From the experimental results using human face images, this method can reconstruct the 3D shape with better accuracy than the previous methods.

KW - 3D shape reconstruction

KW - Convolutional Neural Network

KW - feature learning

UR - http://www.scopus.com/inward/record.url?scp=85048827705&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048827705&partnerID=8YFLogxK

U2 - 10.1109/IWAIT.2018.8369636

DO - 10.1109/IWAIT.2018.8369636

M3 - Conference contribution

AN - SCOPUS:85048827705

SP - 1

EP - 4

BT - 2018 International Workshop on Advanced Image Technology, IWAIT 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -