24 Citations (Scopus)

Abstract

Deep learning techniques have attracted many researchers in computer vision field to solve computer vision problems such as image segmentation and object recognition. This success also led to the implementation of deep learning techniques in 3D reconstruction. 3D reconstruction itself is a classical problem in computer vision that has been approached by many techniques. However, deep learning techniques for 3D reconstruction are still in the early phase, whereas the opportunity of the techniques is large. Hence, to improve the performance of such approaches, it is important to study the research and applications of the approaches through literature review. This paper reviews deep learning-based methods in 3D reconstruction from single or multiple images. The research scope includes single or multiple image sources but excludes RGB-D type input. Several methods and their significance are discussed, also some challenges and research opportunities are proposed for further research directions.

Original languageEnglish
Title of host publicationProceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages327-331
Number of pages5
ISBN (Electronic)9781728121338
DOIs
Publication statusPublished - Jul 2019
Event12th International Conference on Information and Communication Technology and Systems, ICTS 2019 - Surabaya, Indonesia
Duration: 18 Jul 2019 → …

Publication series

NameProceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019

Conference

Conference12th International Conference on Information and Communication Technology and Systems, ICTS 2019
Country/TerritoryIndonesia
CitySurabaya
Period18/07/19 → …

Keywords

  • 3D reconstruction
  • Computer vision
  • Deep learning
  • End-to-end approach
  • Machine learning

Fingerprint

Dive into the research topics of 'A review of deep learning techniques for 3D reconstruction of 2D images'. Together they form a unique fingerprint.

Cite this