Monocular Depth Estimation: A Survey

Abstract

Monocular depth estimation is often described as an ill-posed and inherently ambiguous problem. Estimating depth from 2D images is a crucial step in scene reconstruction, 3Dobject recognition, segmentation, and detection. The problem can be framed as: given a single RGB image as input, predict a dense depth map for each pixel. This problem is worsened by the fact that most scenes have large texture and structural variations, object occlusions, and rich geometric detailing. All these factors contribute to difficulty in accurate depth estimation. In this paper, we review five papers that attempt to solve the depth estimation problem with various techniques including supervised, weakly-supervised, and unsupervised learning techniques. We then compare these papers and understand the improvements made over one another. Finally, we explore potential improvements that can aid to better solve this problem.

8 pages, 1 figure, 4 tables

References in corpus (1)

• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

Cited by in corpus (8)

• Detecting and Identifying Optical Signal Attacks on Autonomous Driving Systems
• MonSter: Awakening the Mono in Stereo
• RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects
• Progressive Depth Learning for Single Image Dehazing
• Marine vessel tracking using a monocular camera
• Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images
• Improved Point Transformation Methods For Self-Supervised Depth Prediction
• A Dark Flash Normal Camera