Three-Dimensional Reconstruction from a Single RGB Image Using Deep Learning: A Review

Performing 3D reconstruction from a single 2D input is a challenging problem that is trending in literature. Until recently, it was an ill-posed optimization problem, but with the advent of learning-based methods, the performance of 3D reconstruction has also significantly improved. Infinitely many...

Full description

Saved in:
Bibliographic Details
Published in:Journal of imaging 2022-08, Vol.8 (9), p.225
Main Authors: Khan, Muhammad Saif Ullah, Pagani, Alain, Liwicki, Marcus, Stricker, Didier, Afzal, Muhammad Zeshan
Format: Article
Language:English
Subjects:
3D reconstruction
Algorithms
Cameras
convolutional neural networks
Datasets
Deep learning
Geometry
Image reconstruction
Literature reviews
Machine Learning
Maskininlärning
Neural networks
Optimization
Review
Teaching methods
textureless surfaces
Three dimensional models
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Performing 3D reconstruction from a single 2D input is a challenging problem that is trending in literature. Until recently, it was an ill-posed optimization problem, but with the advent of learning-based methods, the performance of 3D reconstruction has also significantly improved. Infinitely many different 3D objects can be projected onto the same 2D plane, which makes the reconstruction task very difficult. It is even more difficult for objects with complex deformations or no textures. This paper serves as a review of recent literature on 3D reconstruction from a single view, with a focus on deep learning methods from 2018 to 2021. Due to the lack of standard datasets or 3D shape representation methods, it is hard to compare all reviewed methods directly. However, this paper reviews different approaches for reconstructing 3D shapes as depth maps, surface normals, point clouds, and meshes; along with various loss functions and metrics used to train and evaluate these methods.
ISSN:2313-433X
2313-433X
DOI:10.3390/jimaging8090225