Towards Keypoint Guided Self-Supervised Depth Estimation

Kristijan Bartol, David Bojanić, Tomislav Petković, Tomislav Pribanić, Yago Diez Donoso

2020

Abstract

This paper proposes to use keypoints as a self-supervision clue for learning depth map estimation from a collection of input images. As ground truth depth from real images is difficult to obtain, there are many unsupervised and self-supervised approaches to depth estimation that have been proposed. Most of these unsupervised approaches use depth map and ego-motion estimations to reproject the pixels from the current image into the adjacent image from the image collection. Depth and ego-motion estimations are evaluated based on pixel intensity differences between the correspondent original and reprojected pixels. Instead of reprojecting the individual pixels, we propose to first select image keypoints in both images and then reproject and compare the correspondent keypoints of the two images. The keypoints should describe the distinctive image features well. By learning a deep model with and without the keypoint extraction technique, we show that using the keypoints improve the depth estimation learning. We also propose some future directions for keypoint-guided learning of structure-from-motion problems.

Paper Citation

in Harvard Style

Bartol K., Bojanić D., Petković T., Pribanić T. and Donoso Y. (2020). Towards Keypoint Guided Self-Supervised Depth Estimation. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 583-589. DOI: 10.5220/0009190005830589

in Bibtex Style

@conference{visapp20,
author={Kristijan Bartol and David Bojanić and Tomislav Petković and Tomislav Pribanić and Yago Diez Donoso},
title={Towards Keypoint Guided Self-Supervised Depth Estimation},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP},
year={2020},
pages={583-589},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009190005830589},
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 4: VISAPP
TI - Towards Keypoint Guided Self-Supervised Depth Estimation
SN - 978-989-758-402-2
AU - Bartol K.
AU - Bojanić D.
AU - Petković T.
AU - Pribanić T.
AU - Donoso Y.
PY - 2020
SP - 583
EP - 589
DO - 10.5220/0009190005830589
PB - SciTePress