DepthP+P: Metric Accurate Monocular Depth Estimation using Planar and Parallax
Journal of Soft Computing and Artificial Intelligence · 29.12.2025 · 6 (2) · 29-38
DOI: 10.55195/jscai.1748633 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Soft Computing and Artificial Intelligence, online erschienen am 29.12.2025. Verfasst von Sadra Safadoust und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben.
Abstract (Originalsprache)
Current self-supervised monocular depth estimation methods are mostly based on estimating a rigid-body motion representing camera motion. These methods suffer from the well-known scale ambiguity problem in their predictions. We propose DepthP+P, a method that learns to estimate outputs in metric scale by following the traditional planar parallax paradigm. We first align the two frames using a common ground plane which removes the effect of the rotation component in the camera motion. With two neural networks, we predict the depth and the camera translation, which is easier to predict alone compared to predicting it together with rotation. By assuming a known camera height, we can then calculate the induced 2D image motion of a 3D point and use it for reconstructing the target image in a self-supervised monocular approach. We perform experiments on the KITTI driving dataset and show that the planar parallax approach, which only needs to predict camera translation, can be a metrically accurate alternative to the current methods that rely on estimating 6DoF camera motion.
Zitieren
APA
Safadoust, S., & Guney, F. (2025). DepthP+P: Metric Accurate Monocular Depth Estimation using Planar and Parallax. Journal of Soft Computing and Artificial Intelligence, 6(2), 29-38. https://doi.org/10.55195/jscai.1748633
Vancouver
Safadoust S, Guney F. DepthP+P: Metric Accurate Monocular Depth Estimation using Planar and Parallax. Journal of Soft Computing and Artificial Intelligence. 2025;6(2):29-38. doi:10.55195/jscai.1748633
BibTeX
@article{Safadoust2025,
author = {Safadoust, Sadra and Guney, Fatma},
title = {DepthP+P: Metric Accurate Monocular Depth Estimation using Planar and Parallax},
journal = {Journal of Soft Computing and Artificial Intelligence},
year = {2025},
volume = {6},
number = {2},
pages = {29--38},
doi = {10.55195/jscai.1748633}
}
EUVIMED