CVApr 13, 2021

Single Image Depth Estimation: An Overview

arXiv:2104.06456v1114 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental overview paper summarizing existing solutions for researchers in computer vision and scene understanding.

The paper reviews machine learning methods, particularly convolutional neural networks, for single image depth estimation, covering supervised and unsupervised approaches, multitask learning, and analysis of mechanisms and failure cases.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes