RANSAC-Scaled Depth: A Dual-Teacher Framework for Metric Depth Annotation in Data-Scarce Scenarios
Computer Optics · 01.12.2025 · 1174
DOI: 10.18287/coj1810 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Optics, online erschienen am 01.12.2025. Verfasst von M.V. Lazukov und 3 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben.
Abstract (Originalsprache)
This paper addresses the problem of training metric monocular depth estimation models for specialized domains in the absence of labeled real-world data. We propose a hybrid pseudo-labeling method that combines the predictions of two models: a metric "teacher," trained on synthetic data to obtain the correct scale, and a foundational relative "teacher" for structurally accurate scene geometry and depth. The relative depth map is calibrated via a linear transformation, whose parameters are found using the outlier-robust RANSAC algorithm on a subset of "support" points. Experiments on the KITTI dataset show that the proposed approach improves the quality of the pseudo-labels, reducing the commonly used error metric AbsRel by 21.6 % compared to the baseline method. A compact "student" model trained on these labels demonstrated superiority over the baseline model, achieving a 23.8 % reduction in AbsRel and a 13.8 % reduction in RMSE log. The results confirm that the proposed method significantly improves domain adaptation from general purpose to the specific domain, allowing for the creation of high-precision metric models without the need to collect and annotate volumes of real data.
Zitieren
APA
Lazukov, M., Shoshin, A., Belyaev, P., & Shvets, E. (2025). RANSAC-Scaled Depth: A Dual-Teacher Framework for Metric Depth Annotation in Data-Scarce Scenarios. Computer Optics, 1174. https://doi.org/10.18287/coj1810
Vancouver
Lazukov M, Shoshin A, Belyaev P, Shvets E. RANSAC-Scaled Depth: A Dual-Teacher Framework for Metric Depth Annotation in Data-Scarce Scenarios. Computer Optics. 2025:1174. doi:10.18287/coj1810
BibTeX
@article{Lazukov2025,
author = {Lazukov, M.V. and Shoshin, A.V. and Belyaev, P.V. and Shvets, E.A.},
title = {RANSAC-Scaled Depth: A Dual-Teacher Framework for Metric Depth Annotation in Data-Scarce Scenarios},
journal = {Computer Optics},
year = {2025},
pages = {1174},
doi = {10.18287/coj1810}
}
EUVIMED