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.

Training a single network for high resolution and geometrically consistent monocular depth estimation is challenging due to varying scene complexities in the real world.

This book gathers selected high-impact articles from the 2nd International Conference on Data Science, Machine Learning & Applications 2020.

This is an ideal reference for anyone looking for an understanding of the diverse concepts and ideas around this topic and how we can move towards more general techniques than traditional photometric stereo.

... example, depth completion [38,39,55], which recovers a dense depth map from sparse depth measurements, can be performed more accurately and more reliably than monocular ... Depth Map Decomposition for Monocular Depth Estimation 19.

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.

Convolutional neural networks have shown a remarkable ability to estimate depth from a single image.

... Depth map via monocular dense depth sensing, used to segment out objects in the FOV, depth range target 0.3–30 m, accuracy within 1 % at 1 m, and within 10 % at 30 m – Scene labeling and pixel labeling, based on attributes of segmented ...

Depth estimation from single monocular images is a theoretical challenge in computer vision as well as a computational challenge in practice.