KIT | KIT-Bibliothek | Impressum | Datenschutz

A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation

Landgraf, Steven ORCID iD icon 1; Qin, Rongjun; Ulrich, Markus ORCID iD icon 1
1 Institut für Photogrammetrie und Fernerkundung (IPF), Karlsruher Institut für Technologie (KIT)

Abstract:

While recent foundation models have enabled significant breakthroughs in monocular depth estimation, a clear path towards safe and reliable deployment in the real-world remains elusive. Metric depth estimation, which involves predicting absolute distances, poses particular challenges, as even the most advanced foundation models remain prone to critical errors. Since quantifying the uncertainty has emerged as a promising endeavor to address these limitations and enable trustworthy deployment, we fuse five different uncertainty quantification methods with the current state-of-the-art DepthAnythingV2 foundation model. To cover a wide range of metric depth domains, we evaluate their performance on four diverse datasets. Our findings identify fine-tuning with the Gaussian Negative Log-Likelihood Loss (GNLL) as a particularly promising approach, offering reliable uncertainty estimates while maintaining predictive performance and computational efficiency on par with the baseline, encompassing both training and inference time. By fusing uncertainty quantification and foundation models within the context of monocular depth estimation, this paper lays a critical foundation for future research aimed at improving not only model performance but also its explainability. ... mehr

Zugehörige Institution(en) am KIT Institut für Photogrammetrie und Fernerkundung (IPF)
Publikationstyp Forschungsbericht/Preprint
Publikationsjahr 2025
Sprache Englisch
Identifikator KITopen-ID: 1000178517
Verlag arxiv
Umfang 15 S.
Schlagwörter Computer Vision and Pattern Recognition (cs.CV), Artificial Intelligence (cs.AI), Machine Learning (cs.LG)
Nachgewiesen in arXiv

Volltext §
DOI: 10.5445/IR/1000178517
Veröffentlicht am 28.01.2025
Originalveröffentlichung
DOI: 10.48550/arXiv.2501.08188
Seitenaufrufe: 5
seit 29.01.2025
Downloads: 2
seit 29.01.2025
Cover der Publikation
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page