Home

Awesome

<img height="23" src="https://github.com/lh9171338/Outline/blob/master/icon.jpg"/> Monocular-Depth-Estimation-Papers

A collection of monocular depth estimation papers.

Outline

1. Methods

1.1 Supervised

NamePaperSourceCode/Project
High Quality Monocular Depth Estimation via Transfer LearningarXiv 2018[Code]
SVSSingle View Stereo MatchingCVPR 2018[Code]
DORNDeep Ordinal Regression Network for Monocular Depth EstimationCVPR 2018[Caffe] [PyTorch]
CCRF-CNNMulti-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth EstimationCVPR 2017[Code]
CNN-SLAMCNN-SLAM: Real-time dense monocular SLAM with learned depth predictionCVPR 2017[Code]
A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB ImagesICCV 2017
Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks3DV 2016
FCRNDeeper Depth Prediction with Fully Convolutional Residual Networks3DV 2016[Code]
Deep3DDeep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural NetworksECCV 2016[Code]
Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architectureICCV 2015[Project]
Depth Map Prediction from a Single Image using a Multi-Scale Deep NetworkNIPS 2014[Code]

1.2 Unsupervised

NamePaperSourceCode/Project
Monodepth2Digging into Self-Supervised Monocular Depth PredictionICCV 2019[Code]
Learning Monocular Depth by Distilling Cross-domain Stereo NetworksECCV 2018[Code]
SemoDepthSemi-Supervised Deep Learning for Monocular Depth Map PredictionCVPR 2017[Code]
MonodepthUnsupervised Monocular Depth Estimation with Left-Right ConsistencyCVPR 2017[Project] [Code]
Unsupervised CNN for Single View Depth Estimation: Geometry to the RescueECCV 2016[Code]

1.3 Video based

NamePaperSourceCode/Project
Struct2depthDepth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular VideosAAAI 2019[Project] [Code]
Vid2depthUnsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric ConstraintsCVPR 2018[Project] [Code]
Depth-VO-FeatUnsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature ReconstructionCVPR 2018[Code]
GeoNetGeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera PoseCVPR 2018[Code]
SfMLearnerUnsupervised Learning of Depth and Ego-Motion from VideoCVPR 2017[Code]

2. Datasets

3. SOTA