Literature review on depth estimation using a single image

摘要

Depth estimation is an important component of understanding geometric relations within a scene. Different depth estimation techniques using a single image are analyzed in this survey paper. Depth estimation from a single image is often described as an ill-posed and inherently ambiguous problem. Recovering depth information in applications like 3D modeling, robotics, autonomous driving, etc. is more important when no other information such as stereo images, optical flow, or point clouds are unavailable. For the task of depth estimation using single images, learning based methods have shown very promising results.