Monocular Depth Estimation for Tilted Images via Gravity Rectifier

Yuki Saito, Hideo Saito, Vincent Frémont

2023

Abstract

Monocular depth estimation is a challenging task in computer vision. Although many approaches using Convolutional neural networks (CNNs) have been proposed, most of them are trained on large-scale datasets mainly composed of gravity-aligned images. Therefore, conventional approaches fail to predict reliable depth for tilted images containing large pitch and roll camera rotations. To tackle this problem, we propose a novel refining method based on the distribution of gravity directions in the training sets. We designed a gravity rectifier that is learned to transform the gravity direction of a tilted image into a rectified one that matches the gravity-aligned training data distribution. For the evaluation, we employed public datasets and also created our own dataset composed of large pitch and roll camera movements. Our experiments showed that our approach successfully rectified the camera rotation and outperformed our baselines, which achieved 29% im-provement in abs rel over the vanilla model. Additionally, our method had competitive accuracy comparable to state-of-the-art monocular depth prediction approaches considering camera rotation.

Paper Citation

in Harvard Style

Saito Y., Saito H. and Frémont V. (2023). Monocular Depth Estimation for Tilted Images via Gravity Rectifier. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 453-463. DOI: 10.5220/0011624600003417

in Bibtex Style

@conference{visapp23,
author={Yuki Saito and Hideo Saito and Vincent Frémont},
title={Monocular Depth Estimation for Tilted Images via Gravity Rectifier},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={453-463},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011624600003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - Monocular Depth Estimation for Tilted Images via Gravity Rectifier
SN - 978-989-758-634-7
AU - Saito Y.
AU - Saito H.
AU - Frémont V.
PY - 2023
SP - 453
EP - 463
DO - 10.5220/0011624600003417
PB - SciTePress