Smartphone Video-based Monocular 3D Reconstruction

Authors

Hussam Azzuni, Mohamed Bin Zayed University of Artificial IntelligenceFollow
Mustaqeem Khan, Mohamed Bin Zayed University of Artificial IntelligenceFollow
Abdulmotaleb Elsaddik, University of Ottawa
Wail Gueaieb, University of Ottawa

Document Type

Article

Publication Title

IEEE Consumer Electronics Magazine

Abstract

Neural Radiance Fields (NeRFs) have rapidly progressed in novel view synthesis, enabling photorealistic 3D scene reconstruction. However, achieving precise 3D models requires expensive equipment. The primary focus of this study is enhancing NeRF-based 3D reconstruction using RGB smartphone sensors. In this work, we provide a guide for capturing videos of indoor and outdoor scenes to ensure successful 3D reconstruction using a smartphone. This includes algorithms for automatically removing artifacts and irrelevant points from the captured video data.

DOI

10.1109/MCE.2024.3402848

Publication Date

1-1-2024

Keywords

Cameras, Laser radar, Point cloud compression, Semantics, Sensors, Solid modeling, Three-dimensional displays

Recommended Citation

H. Azzuni et al., "Smartphone Video-based Monocular 3D Reconstruction," IEEE Consumer Electronics Magazine, Jan 2024.

The definitive version is available at https://doi.org/10.1109/MCE.2024.3402848