During this project, state-of-the-art deep learning models have been used to estimate depth maps from a monocular RGB image applying a teacher-student learning approach.

This work focuses on using these feature-based sparse patterns to generate additional depth information by interpolating regions between clusters of samples that are in close proximity to each other.

Under appropriate initialization conditions, direct image comparison allows the direct method to perform relative positioning without a map, which enables the algorithm to work in many environments without external positioning equipment, ...

Monocular depth estimation is a challenging but significant part of computer vision with many applications in other areas of study.

... estimation is use- ful in various applications like robotics and autonomous navigation . Any deep learning workflow to estimate ... deep. Check for QuMaDe: Quick Foreground Mask and Monocular Depth Data Generation 1 Introduction.

This thesis evaluates and profiles a monocular depth estimation algorithm in which depth maps are generated from a single image using a non-parametric depth transfer approach. 3D depth from images has a wide range of applications in ...