Monocular Depth Estimation Based On Deep Learning: An Overview

Abstract

Depth information is important for autonomous systems to perceive environments and estimate their own state. Traditional depth estimation methods, like structure from motion and stereo vision matching, are built on feature correspondences of multiple viewpoints. Meanwhile, the predicted depth maps are sparse. Inferring depth information from a single image (monocular depth estimation) is an ill-posed problem. With the rapid development of deep neural networks, monocular depth estimation based on deep learning has been widely studied recently and achieved promising performance in accuracy. Meanwhile, dense depth maps are estimated from single images by deep neural networks in an end-to-end manner. In order to improve the accuracy of depth estimation, different kinds of network frameworks, loss functions and training strategies are proposed subsequently. Therefore, we survey the current monocular depth estimation methods based on deep learning in this review. Initially, we conclude several widely used datasets and evaluation indicators in deep learning-based depth estimation. Furthermore, we review some representative existing methods according to different training manners: supervised, unsupervised and semi-supervised. Finally, we discuss the challenges and provide some ideas for future researches in monocular depth estimation.

14 pages, 4 figures

References in corpus (21)

• Conditional Generative Adversarial Nets
• ORB-SLAM: a Versatile and Accurate Monocular SLAM System
• A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• How Generative Adversarial Networks and Their Variants Work: An Overview
• SfM-Net: Learning of Structure and Motion from Video
• Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
• End-to-End Learning of Geometry and Context for Deep Stereo Regression
• Argoverse: 3D Tracking and Forecasting with Rich Maps
• GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks
• Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video
• Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency
• Single-Image Depth Perception in the Wild
• SGANVO: Unsupervised Deep Visual Odometry and Depth Estimation with Stacked Generative Adversarial Networks
• Deep Direct Visual Odometry
• Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depth
• Learning Depth with Convolutional Spatial Propagation Network
• The BerHu penalty and the grouped effect
• Unsupervised Learning of Monocular Depth and Ego-Motion Using Multiple Masks

Cited by in corpus (21)

• MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer
• Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey
• Masked GANs for Unsupervised Depth and Pose Prediction with Scale Consistency
• Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey
• Run-Time Monitoring of Machine Learning for Robotic Perception: A Survey of Emerging Trends
• Radar Voxel Fusion for 3D Object Detection
• Deep Direct Visual Odometry
• Towards Safer Robot-Assisted Surgery: A Markerless Augmented Reality Framework
• altiro3D: Scene representation from single image and novel view synthesis
• SinkSAM-Net: Knowledge-Driven Self-Supervised Sinkhole Segmentation Using Topographic Priors and Segment Anything Model
• Active Safety Envelopes using Light Curtains with Probabilistic Guarantees
• RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects
• A Framework for 3D Tracking of Frontal Dynamic Objects in Autonomous Cars
• Regularising disparity estimation via multi task learning with structured light reconstruction
• MSFNet:Multi-scale features network for monocular depth estimation
• Multi-task GANs for Semantic Segmentation and Depth Completion with Cycle Consistency
• A Hybrid mmWave and Camera System for Long-Range Depth Imaging
• Deep Structure Learning using Feature Extraction in Trained Projection Space
• Depth Estimation using Weighted-loss and Transfer Learning
• Depth estimation on embedded computers for robot swarms in forest
• Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANs