3D Reconstruction from a Single RGB Image using Deep Learning: A Review

Muhammad Saif Ullah Khan; Alain Pagani; Marcus Liwicki; Didier Stricker; Muhammad Zeshan Afzal

In: Journal of Imaging (MDPI J), Vol. 8, No. 225, Pages 1-23, MDPI, 8/2022.


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.


Khan2022_JImaging.pdf (pdf, 3 MB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence