Self-Supervised Scale Recovery for Monocular Depth and Egomotion Estimation
arXiv:2009.03787 · doi:10.1109/IROS51168.2021.9635938
Abstract
The self-supervised loss formulation for jointly training depth and egomotion neural networks with monocular images is well studied and has demonstrated state-of-the-art accuracy. One of the main limitations of this approach, however, is that the depth and egomotion estimates are only determined up to an unknown scale. In this paper, we present a novel scale recovery loss that enforces consistency between a known camera height and the estimated camera height, generating metric (scaled) depth and egomotion predictions. We show that our proposed method is competitive with other scale recovery techniques that require more information. Further, we demonstrate that our method facilitates network retraining within new environments, whereas other scale-resolving approaches are incapable of doing so. Notably, our egomotion network is able to produce more accurate estimates than a similar method which recovers scale at test time only.
In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'21), Prague, Czech Republic, Sept. 27 - Oct. 1, 2021
References in corpus (3)
Cited by in corpus (6)
- Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Driving
- On the Coupling of Depth and Egomotion Networks for Self-Supervised Structure from Motion
- MonoPP: Metric-Scaled Self-Supervised Monocular Depth Estimation by Planar-Parallax Geometry in Automotive Applications
- TanDepth: Leveraging Global DEMs for Metric Monocular Depth Estimation in UAVs
- Accurate and Robust Scale Recovery for Monocular Visual Odometry Based on Plane Geometry
- Data-driven Holistic Framework for Automated Laparoscope Optimal View Control with Learning-based Depth Perception