Single-View 3D Reconstruction Review

sellReview Paper sell3d reconstruction sellsingle-view selldeep learning

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 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.

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

Read Full-Text

How to Cite

Please include the following citation if you refer to this publication in your work:

@article{jimaging8090225,
    author={Khan, Muhammad Saif Ullah and Pagani, Alain and Liwicki, Marcus and Stricker, Didier and Afzal, Muhammad Zeshan},
    title={Three-Dimensional Reconstruction from a Single RGB Image Using Deep Learning: A Review},
    journal={Journal of Imaging},
    volume={8},
    year={2022},
    number={9},
    article-number={225},
    url={https://www.mdpi.com/2313-433X/8/9/225},
    pubmedid={36135391},
    issn={2313-433X},
    doi={10.3390/jimaging8090225}
}

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.