Calibrating Self-supervised Monocular Depth Estimation
This addresses a practical limitation for applications in robotics and autonomous systems by eliminating the need for additional sensors like LiDAR.
The paper tackles the problem of unknown scaling factor in self-supervised monocular depth estimation by incorporating prior information about camera configuration and environment, enabling direct depth prediction without relying on LiDAR ground truth at test time.
In the recent years, many methods demonstrated the ability of neural networks to learn depth and pose changes in a sequence of images, using only self-supervision as the training signal. Whilst the networks achieve good performance, the often over-looked detail is that due to the inherent ambiguity of monocular vision they predict depth up to an unknown scaling factor. The scaling factor is then typically obtained from the LiDAR ground truth at test time, which severely limits practical applications of these methods. In this paper, we show that incorporating prior information about the camera configuration and the environment, we can remove the scale ambiguity and predict depth directly, still using the self-supervised formulation and not relying on any additional sensors.