LineGraph2Road: Structural Graph Reasoning on Line Graphs for Road Network Extraction

TL;DR

LineGraph2Road is proposed, a framework that improves connectedness prediction by formulating it as binary classification over edges in a constructed global but sparse Euclidean graph, where nodes are keypoints extracted from segmentation masks and edges connect node pairs within a predefined distance threshold, representing potential road segments.

Abstract

The accurate and automatic extraction of roads from satellite imagery is critical for applications in navigation and urban planning, significantly reducing the need for manual annotation. Many existing methods decompose this task into keypoint extraction and connectedness prediction, but often struggle to capture long-range dependencies and complex topologies. Here, we propose LineGraph2Road, a framework that improves connectedness prediction by formulating it as binary classification over edges in a constructed global but sparse Euclidean graph, where nodes are keypoints extracted from segmentation masks and edges connect node pairs within a predefined distance threshold, representing potential road segments. To better learn structural link representation, we transform the original graph into its corresponding line graph and apply a Graph Transformer on it for connectedness prediction. This formulation overcomes the limitations of endpoint-embedding fusion on set-isomorphic links, enabling rich link representations and effective relational reasoning over the global structure. Additionally, we introduce an overpass/underpass head to resolve multi-level crossings and a coupled NMS strategy to preserve critical connections. We evaluate LineGraph2Road on three benchmarks: City-scale, SpaceNet, and Global-scale, and show that it achieves state-of-the-art results on two key metrics, TOPO-F1 and APLS. It also captures fine visual details critical for real-world deployment. We will make our code publicly available.

Figures (14)

• Figure 1: Comparison of graph connectivity strategies. (a) Local-only (e.g., SAM-Road hetang2024segment) limits message passing to small subgraphs. (b) Fully-connected (e.g., Any2Graph krzakala2024any2graph, RelationFormer shit2022relationformer) enables global reasoning but is computationally costly and structurally uninformed. (c) global but sparse Euclidean graph connects nearby nodes within a distance threshold, balancing global context, structural awareness, and efficiency.
• Figure 2: Overview of our LineGraph2Road pipeline. During both training and inference, a satellite image is processed by the pre-trained SAM encoder kirillov2023segment to extract feature maps, which are decoded into road masks. In training, the graph is constructed from a preprocessed candidate edge set (brown lines), while in inference, it is built from vertices extracted via Coupled NMS on the road mask. This graph is converted into a line graph and passed to a Graph Transformer for binary node classification, determining the presence of links and yielding the final road network graph.
• Figure 3: The visualized road network graph predictions of our method and other baseline methods on City-Scale dataset. (a) small roundabouts; (b) multi-lane highways with complex merges and curves; and (c) winding roads with irregular geometries.
• Figure 4: The visualized road network graph predictions of our method and other baseline methods as well as the predicted overpass/underpass mask on City-Scale dataset, illustrating performance on overpass and underpass crossings.
• Figure 5: NMS vs Couple NMS. (a) Situation that will happen in NMS strategies used in hetang2024segmentyin2024towards. (b) How coupled NMS avoid this situation.

Theorems & Definitions (7)

• definition thmcounterdefinition
• lemma thmcounterlemma
• definition thmcounterdefinition
• definition thmcounterdefinition
• definition thmcounterdefinition
• theorem thmcountertheorem
• lemma thmcounterlemma