Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion

18 Apr 2023  ·  Zeeshan Khan Suri ·

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.

PDF Abstract


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Monocular Depth Estimation KITTI Eigen split unsupervised pc4consistentdepth absolute relative error 0.113 # 34
Egocentric Pose Estimation Kitti Odometry pc4consistentdepth Absolute Trajectory Error [m] 0.014 # 1


No methods listed for this paper. Add relevant methods here