PTC-Depth: Pose-Refined Monocular Depth Estimation with Temporal Consistency
This work addresses jitter and failure issues in depth estimation for real-world robotic applications, representing an incremental improvement by integrating existing methods with new data sources.
The paper tackles the problem of temporal inconsistency in monocular depth estimation for autonomous vehicles and mobile robots by proposing a framework that uses wheel odometry and optical flow to refine depth predictions, achieving robust and accurate performance across multiple datasets.
Monocular depth estimation (MDE) has been widely adopted in the perception systems of autonomous vehicles and mobile robots. However, existing approaches often struggle to maintain temporal consistency in depth estimation across consecutive frames. This inconsistency not only causes jitter but can also lead to estimation failures when the depth range changes abruptly. To address these challenges, this paper proposes a consistency-aware monocular depth estimation framework that leverages wheel odometry from a mobile robot to achieve stable and coherent depth predictions over time. Specifically, we estimate camera pose and sparse depth from triangulation using optical flow between consecutive frames. The sparse depth estimates are used to update a recursive Bayesian estimate of the metric scale, which is then applied to rescale the relative depth predicted by a pre-trained depth estimation foundation model. The proposed method is evaluated on the KITTI, TartanAir, MS2, and our own dataset, demonstrating robust and accurate depth estimation performance.