Awesome

<img height="23" src="https://github.com/lh9171338/Outline/blob/master/icon.jpg"/> Road Extraction Papers

A collection of road extraction papers.

Outline

Methods
Datasets
SOTA

1. Methods

1.1 Road Graph Extraction

Name	Paper	Source	Code/Project
Sat2Graph	Sat2Graph: Road Graph Extraction through Graph-Tensor Encoding	ECCV 2020	[Code]
RoadTagger	RoadTagger: Robust Road Attribute Inference with Graph Neural Networks	AAAI 2020	[Code]
VecRoad	VecRoad: Point-Based Iterative Graph Exploration for Road Graphs Extraction	CVPR 2020	[Project] [Code]
PolyMapper	Topological Map Extraction From Overhead Images	ICCV 2019
NTG	Neural Turtle Graphics for Modeling City Road Layouts	ICCV 2019	[Project]
GGT	Image-Conditioned Graph Generation for Road Network Extraction	NIPS 2019	[Project] [Code]
	Improved Road Connectivity by Joint Learning of Orientation and Segmentation	CVPR 2019	[Code]
RoadTracer	RoadTracer: Automatic Extraction of Road Networks from Aerial Images	CVPR 2018	[Project] [Code]
	Iterative Deep Learning for Road Topology Extraction	BMVC 2018	[Code]
DeepRoadMapper	DeepRoadMapper: Extracting Road Topology from Aerial Images	ICCV 2017

1.2 Road Segmentation

Name	Paper	Source	Code/Project
DiResNet	DiResNet: Direction-aware Residual Network for Road Extraction in VHR Remote Sensing Images	TGRS 2020	[Code]
SII-Net	Spatial Information Inference Net: Road Extraction Using Road-Specific Contextual Information	ISPRS 2019	[Code]
D-LinkNet	D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction	CVPRW 2018	[Code]
	Fully Convolutional Network for Automatic Road Extraction from Satellite Imagery	CVPRW 2018
EOSResUNet	Road detection with EOSResUNet and post vectorizing algorithm	CVPRW 2018
	Stacked U-Nets with Multi-output for Road Extraction	CVPRW 2018
	Roadmap Generation using a Multi-stage Ensemble of Deep Neural Networks with Smoothing-Based Optimization	CVPRW 2018
ResUNet	Road Extraction by Deep Residual U-Net	LGRS 2018	[Code]

1.3 Road Centerline Extraction

Name	Paper	Source	Code/Project
RoadNet	RoadNet: Learning to Comprehensively Analyze Road Networks in Complex Urban Scenes From High-Resolution Remotely Sensed Images	TGRS 2019	[Code]
RCNN-UNet	Road Detection and Centerline Extraction Via Deep Recurrent Convolutional Neural Network U-Net	TGRS 2019
MatAN	Matching Adversarial Networks	CVPR 2018
CasNet	Automatic Road Detection and Centerline Extraction via Cascaded End-to-End Convolutional Neural Network	TGRS 2017

2. Datasets

3. SOTA