Deep Depth Completion of Low-cost Sensor Indoor RGB-D using Euclidean Distance-based Weighted Loss and Edge-aware Refinement

Augusto R. Castro, Valdir Grassi Jr., Moacir A. Ponti

2022

Abstract

Low-cost depth-sensing devices can provide real-time depth maps to many applications, such as robotics and augmented reality. However, due to physical limitations in the acquisition process, the depth map obtained can present missing areas corresponding to irregular, transparent, or reflective surfaces. Therefore, when there is more computing power than just the embedded processor in low-cost depth sensors, models developed to complete depth maps can boost the system's performance. To exploit the generalization capability of deep learning models, we propose a method composed of a U-Net followed by a refinement module to complete depth maps provided by Microsoft Kinect. We applied the Euclidean distance transform in the loss function to increase the influence of missing pixels when adjusting our network filters and reduce blur in predictions. We outperform state-of-the-art methods for completed depth maps in a benchmark dataset. Our novel loss function combining the distance transform, gradient and structural similarity measure presents promising results in guiding the model to reduce unnecessary blurring of final depth maps predicted by a convolutional network.

Download


Paper Citation


in Harvard Style

Castro A., Grassi Jr. V. and Ponti M. (2022). Deep Depth Completion of Low-cost Sensor Indoor RGB-D using Euclidean Distance-based Weighted Loss and Edge-aware Refinement. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 204-212. DOI: 10.5220/0010915300003124


in Bibtex Style

@conference{visapp22,
author={Augusto R. Castro and Valdir Grassi Jr. and Moacir A. Ponti},
title={Deep Depth Completion of Low-cost Sensor Indoor RGB-D using Euclidean Distance-based Weighted Loss and Edge-aware Refinement},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={204-212},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010915300003124},
isbn={978-989-758-555-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - Deep Depth Completion of Low-cost Sensor Indoor RGB-D using Euclidean Distance-based Weighted Loss and Edge-aware Refinement
SN - 978-989-758-555-5
AU - Castro A.
AU - Grassi Jr. V.
AU - Ponti M.
PY - 2022
SP - 204
EP - 212
DO - 10.5220/0010915300003124
PB - SciTePress