150249 20251017144629.0 doi 10.1109/LRA.2022.3142915 sideral 128415 ART-2022-128415 eng Rodriguez-Puigvert, J. Bayesian Deep Neural Networks for Supervised Learning of Single-View Depth 2022 Uncertainty quantification is essential for robotic perception, as overconfident or point estimators can lead to collisions and damages to the environment and the robot. In this letter, we evaluate scalable approaches to uncertainty quantification in single-view supervised depth learning, specifically MC dropout and deep ensembles. For MC dropout, in particular, we explore the effect of the dropout at different levels in the architecture. We show that adding dropout in all layers of the encoder brings better results than other variations found in the literature. This configuration performs similarly to deep ensembles with a much lower memory footprint, which is relevant for applications. Finally, we explore the use of depth uncertainty for pseudo-RGBD ICP and demonstrate its potential to estimate accurate two-view relative motion with the real scale. 2377-3766 © 2022 IEEE. info:eu-repo/semantics/closedAccess All rights reserved http://www.europeana.eu/rights/rr-f/ 5.2 2022 ROBOTICS 10 / 30 = 0.333 2022 Q2 T2 1.693 2022 Artificial Intelligence 2022 Q1 Biomedical Engineering 2022 Q1 Computer Science Applications 2022 Q1 Mechanical Engineering 2022 Q1 Control and Optimization 2022 Q1 Control and Systems Engineering 2022 Q1 Human-Computer Interaction 2022 Q1 Computer Vision and Pattern Recognition 2022 Q1 7.6 2022 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Martinez-Cantin, R. Universidad de Zaragoza (orcid)0000-0002-6741-844X Civera Sancho, J. Universidad de Zaragoza (orcid)0000-0003-1368-1151 5007 520 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Ingen.Sistemas y Automát. 7, 2 (2022), 2565-2572 IEEE Robot. autom. let. IEEE Robotics and Automation Letters 2377-3766 3510363 http://zaguan.unizar.es/record/150249/files/texto_completo.pdf Versión publicada 3156596 http://zaguan.unizar.es/record/150249/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:150249 articulos driver 2025-10-17-14:25:40 ARTICLE