Revisiting Self-supervised Monocular Depth Estimation

Abstract

Self-supervised learning of depth map prediction and motion estimation from monocular video sequences is of vital importance-since it realizes a broad range of tasks in robotics and autonomous vehicles. A large number of research efforts have enhanced the performance by tackling illumination variation, occlusions, and dynamic objects, to name a few. However, each of those efforts targets individual goals and endures as separate works. Moreover, most of previous works have adopted the same CNN weights for initialization, not reaping recent advances in self-supervised feature learning. Therefore, the need to investigate the inter-dependency of the previous methods and the effect of different initial features remains. To achieve these objectives, we revisit numerous previously proposed self-supervised methods for joint learning of depth and motion, perform a comprehensive empirical study, and unveil multiple crucial insights.