Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion
From MaRDI portal
Publication:6433487
arXiv2304.08916MaRDI QIDQ6433487FDOQ6433487
Authors: Zeeshan Khan Suri 
Publication date: 18 April 2023
Abstract: Self-supervised monocular depth estimation approaches suffer not only from scale ambiguity but also infer temporally inconsistent depth maps w.r.t. scale. While disambiguating scale during training is not possible without some kind of ground truth supervision, having scale consistent depth predictions would make it possible to calculate scale once during inference as a post-processing step and use it over-time. With this as a goal, a set of temporal consistency losses that minimize pose inconsistencies over time are introduced. Evaluations show that introducing these constraints not only reduces depth inconsistencies but also improves the baseline performance of depth and ego-motion prediction.
Has companion code repository: https://github.com/zshn25/pc4consistentdepth
This page was built for publication: Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6433487)
