Single Image Depth Estimation: An Overview

Abstract

We review solutions to the problem of depth estimation, arguably the most important subtask in scene understanding. We focus on the single image depth estimation problem. Due to its properties, the single image depth estimation problem is currently best tackled with machine learning methods, most successfully with convolutional neural networks. We provide an overview of the field by examining key works. We examine non-deep learning approaches that mostly predate deep learning and utilize hand-crafted features and assumptions, and more recent works that mostly use deep learning techniques. The single image depth estimation problem is tackled first in a supervised fashion with absolute or relative depth information acquired from human or sensor-labeled data, or in an unsupervised way using unlabelled stereo images or video datasets. We also study multitask approaches that combine the depth estimation problem with related tasks such as semantic segmentation and surface normal estimation. Finally, we discuss investigations into the mechanisms, principles, and failure cases of contemporary solutions.

This is a preprint

References in corpus (5)

• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• AdaBins: Depth Estimation using Adaptive Bins
• DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling
• SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth
• Stochastic Optimization of Sorting Networks via Continuous Relaxations