From Depth Sensing to Deep Depth Estimation for 3D Reconstruction: Open Challenges

Charles Hamesse, Charles Hamesse, Hiep Luong, Rob Haelterman

2023

Abstract

For a few years, techniques based on deep learning for dense depth estimation from monocular RGB frames have increasingly emerged as potential alternatives to 3D sensors such as depth cameras to perform 3D reconstruction. Recent works mention more and more interesting capabilities: estimation of high resolution depth maps, handling of occlusions, or fast execution on various hardware platforms, to name a few. However, it remains unclear whether these methods could actually replace depth cameras, and if so, in which scenario it is really beneficial to do so. In this paper, we show that the errors made by deep learning methods for dense depth estimation have a specific nature, very different from that of depth maps acquired from depth cameras (be it with stereo vision, time-of-flight or other technologies). We take a voluntarily high vantage point and analyze the state-of-the-art dense depth estimation techniques and depth sensors in a hand-picked test scene, in the aim of better understanding the current strengths and weaknesses of different methods and providing guidelines for the design of robust systems which rely on dense depth perception for 3D reconstruction.

Paper Citation

in Harvard Style

Hamesse C., Luong H. and Haelterman R. (2023). From Depth Sensing to Deep Depth Estimation for 3D Reconstruction: Open Challenges. In Proceedings of the 3rd International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE, ISBN 978-989-758-642-2, SciTePress, pages 164-171. DOI: 10.5220/0011972900003497

in Bibtex Style

@conference{improve23,
author={Charles Hamesse and Hiep Luong and Rob Haelterman},
title={From Depth Sensing to Deep Depth Estimation for 3D Reconstruction: Open Challenges},
booktitle={Proceedings of the 3rd International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE,},
year={2023},
pages={164-171},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011972900003497},
isbn={978-989-758-642-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE,
TI - From Depth Sensing to Deep Depth Estimation for 3D Reconstruction: Open Challenges
SN - 978-989-758-642-2
AU - Hamesse C.
AU - Luong H.
AU - Haelterman R.
PY - 2023
SP - 164
EP - 171
DO - 10.5220/0011972900003497
PB - SciTePress