DA-NET: Monocular Depth Estimation using Disparity Maps Awareness NETwork

Antoine Billy, Antoine Billy, Pascal Desbarats

2020

Abstract

Estimating depth from 2D images has become an active field of study in autonomous driving, scene reconstruction, 3D object recognition, segmentation, and detection. Best performing methods are based on Convolutional Neural Networks, and, as the process of building an appropriate set of data requires a tremendous amount of work, almost all of them rely on the same benchmark to compete between each other : The KITTI benchmark. However, most of them will use the ground truth generated by the LiDAR sensor which generates very sparse depth map with sometimes less than 5% of the image density, ignoring the second image that is given for stereo estimation. Recent approaches have shown that the use of both input images given in most of the depth estimation data set significantly improve the generated results. This paper is in line with this idea, we developed a very simple yet efficient model based on the U-NET architecture that uses both stereo images in the training process. We demonstrate the effectiveness of our approach and show high quality results comparable to state-of-the-art methods on the KITTI benchmark.

Paper Citation

in Harvard Style

Billy A. and Desbarats P. (2020). DA-NET: Monocular Depth Estimation using Disparity Maps Awareness NETwork. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 529-535. DOI: 10.5220/0009174405290535

in Bibtex Style

@conference{visapp20,
author={Antoine Billy and Pascal Desbarats},
title={DA-NET: Monocular Depth Estimation using Disparity Maps Awareness NETwork},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={529-535},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009174405290535},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - DA-NET: Monocular Depth Estimation using Disparity Maps Awareness NETwork
SN - 978-989-758-402-2
AU - Billy A.
AU - Desbarats P.
PY - 2020
SP - 529
EP - 535
DO - 10.5220/0009174405290535
PB - SciTePress