Towards Real-Time Monocular Depth Estimation for Robotics: A Survey

As an essential component for many autonomous driving and robotic activities such as ego-motion estimation, obstacle avoidance scene understanding, monocular depth estimation (MDE) has attracted great attention from the computer vision robotics communities. Over past decades, a large number of methods have been developed. To best our knowledge, however, there is not comprehensive survey MDE. This paper aims to bridge this gap by reviewing 197 relevant articles published between 1970 2021. In particular, we provide MDE covering various methods, introduce popular performance evaluation metrics summarize publically available datasets. We also open-source implementations some representative compare their performances. Furthermore, review application in important tasks. Finally, conclude presenting promising directions future research. expected assist readers navigate research field.