Home

Awesome

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

A collection of road extraction papers.

Outline

1. Methods

1.1 Road Graph Extraction

NamePaperSourceCode/Project
Sat2GraphSat2Graph: Road Graph Extraction through Graph-Tensor EncodingECCV 2020[Code]
RoadTaggerRoadTagger: Robust Road Attribute Inference with Graph Neural NetworksAAAI 2020[Code]
VecRoadVecRoad: Point-Based Iterative Graph Exploration for Road Graphs ExtractionCVPR 2020[Project] [Code]
PolyMapperTopological Map Extraction From Overhead ImagesICCV 2019
NTGNeural Turtle Graphics for Modeling City Road LayoutsICCV 2019[Project]
GGTImage-Conditioned Graph Generation for Road Network ExtractionNIPS 2019[Project] [Code]
Improved Road Connectivity by Joint Learning of Orientation and SegmentationCVPR 2019[Code]
RoadTracerRoadTracer: Automatic Extraction of Road Networks from Aerial ImagesCVPR 2018[Project] [Code]
Iterative Deep Learning for Road Topology ExtractionBMVC 2018[Code]
DeepRoadMapperDeepRoadMapper: Extracting Road Topology from Aerial ImagesICCV 2017

1.2 Road Segmentation

NamePaperSourceCode/Project
DiResNetDiResNet: Direction-aware Residual Network for Road Extraction in VHR Remote Sensing ImagesTGRS 2020[Code]
SII-NetSpatial Information Inference Net: Road Extraction Using Road-Specific Contextual InformationISPRS 2019[Code]
D-LinkNetD-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road ExtractionCVPRW 2018[Code]
Fully Convolutional Network for Automatic Road Extraction from Satellite ImageryCVPRW 2018
EOSResUNetRoad detection with EOSResUNet and post vectorizing algorithmCVPRW 2018
Stacked U-Nets with Multi-output for Road ExtractionCVPRW 2018
Roadmap Generation using a Multi-stage Ensemble of Deep Neural Networks with Smoothing-Based OptimizationCVPRW 2018
ResUNetRoad Extraction by Deep Residual U-NetLGRS 2018[Code]

1.3 Road Centerline Extraction

NamePaperSourceCode/Project
RoadNetRoadNet: Learning to Comprehensively Analyze Road Networks in Complex Urban Scenes From High-Resolution Remotely Sensed ImagesTGRS 2019[Code]
RCNN-UNetRoad Detection and Centerline Extraction Via Deep Recurrent Convolutional Neural Network U-NetTGRS 2019
MatANMatching Adversarial NetworksCVPR 2018
CasNetAutomatic Road Detection and Centerline Extraction via Cascaded End-to-End Convolutional Neural NetworkTGRS 2017

2. Datasets

3. SOTA