# Segment Anything Model for Road Network Graph Extraction

arXiv: https://arxiv.org/abs/2403.16051 · HTML: https://mlsanity.com/paper/2403.16051/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 71 references that are in the map.
- First posted on arXiv 24 Mar 2024.

## Builds on (most cited first, 30 of 46)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation](https://mlsanity.com/paper/2005.04259/) (2020)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis](https://mlsanity.com/paper/2111.04276/) (2021)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [TNT: Target-driveN Trajectory Prediction](https://mlsanity.com/paper/2008.08294/) (2020)
- [Remote Sensing Image Change Detection with Transformers](https://mlsanity.com/paper/2103.00208/) (2021)
- [HDMapNet: An Online HD Map Construction and Evaluation Framework](https://mlsanity.com/paper/2107.06307/) (2021)
- [Customized Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.13785/) (2023)
- [PolyGen: An Autoregressive Generative Model of 3D Meshes](https://mlsanity.com/paper/2002.10880/) (2020)

## Built on by (most cited first, 28 of 28)

- [RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent](https://mlsanity.com/paper/2406.07089/) (2024)
- [SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models](https://mlsanity.com/paper/2411.13112/) (2024)
- [Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model](https://mlsanity.com/paper/2406.19369/) (2024)
- [Towards Satellite Image Road Graph Extraction: A Global-Scale Dataset and A Novel Method](https://mlsanity.com/paper/2411.16733/) (2024)
- [UrbanSAM: Learning Invariance-Inspired Adapters for Segment Anything Models in Urban Construction](https://mlsanity.com/paper/2502.15199/) (2025)
- [IRSAMap:Towards Large-Scale, High-Resolution Land Cover Map Vectorization](https://mlsanity.com/paper/2508.16272/) (2025)
- [From Ideal to Real: Unified and Data-Efficient Dense Prediction for Real-World Scenarios](https://mlsanity.com/paper/2506.20279/) (2025)
- [GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs](https://mlsanity.com/paper/2502.11731/) (2025)
- [GLD-Road:A global-local decoding road network extraction model for remote sensing images](https://mlsanity.com/paper/2506.09553/) (2025)
- [DIGMAPPER: A Modular System for Automated Geologic Map Digitization](https://mlsanity.com/paper/2506.16006/) (2025)
- [LayoutGKN: Graph Similarity Learning of Floor Plans](https://mlsanity.com/paper/2509.03737/) (2025)
- [Flood Mapping from RGB imagery using a Vision Foundation Model](https://mlsanity.com/paper/2606.24120/) (2026)
- [TerraDiT-Omega: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive](https://mlsanity.com/paper/2606.31029/) (2026)
- [InterLoc: LiDAR-based Intersection Localization using Road Segmentation with Automated Evaluation Method](https://mlsanity.com/paper/2505.00512/) (2025)
- [Bridging the Gap Between Sparsity and Redundancy: A Dual-Decoding Framework with Global Context for Map Inference](https://mlsanity.com/paper/2509.11731/) (2025)
- [UniVector: Unified Vector Extraction via Instance-Geometry Interaction](https://mlsanity.com/paper/2510.13234/) (2025)
- [EucliDreamer: Fast and High-Quality Texturing for 3D Models with Depth-Conditioned Stable Diffusion](https://mlsanity.com/paper/2404.10279/) (2024)
- [SAM Encoder Breach by Adversarial Simplicial Complex Triggers Downstream Model Failures](https://mlsanity.com/paper/2508.06127/) (2025)
- [DeH4R: A Decoupled and Hybrid Method for Road Network Graph Extraction](https://mlsanity.com/paper/2508.13669/) (2025)
- [DOGE: Differentiable Bezier Graph Optimization for Road Network Extraction](https://mlsanity.com/paper/2511.19850/) (2025)
- [Beyond Endpoints: Path-Centric Reasoning for Vectorized Off-Road Network Extraction](https://mlsanity.com/paper/2512.10416/) (2025)
- [LineGraph2Road: Structural Graph Reasoning on Line Graphs for Road Network Extraction](https://mlsanity.com/paper/2602.23290/) (2026)
- [Laplacian Frequency Interaction Network for Rural Thematic Road Extraction](https://mlsanity.com/paper/2605.02866/) (2026)
- [Vector Map as Language: Toward Unified Remote Sensing Vector Mapping](https://mlsanity.com/paper/2606.10701/) (2026)
- [TraversRL: Traversable Pedestrian Pathway Generation With Reinforcement Learning](https://mlsanity.com/paper/2607.17479/) (2026)
- [Distilled Roads: Generalisable Road Network Extraction Across Sensors, Resolutions, and Region](https://mlsanity.com/paper/2608.03407/) (2026)
- [VisAdj: Learning Adjacency Matrices from Node-Link Images](https://mlsanity.com/paper/2608.21825/) (2026)
- [Genesis: A Generative Engine for Hierarchical Satellite Image Synthesis](https://mlsanity.com/paper/2609.02683/) (2026)

## Abstract (arXiv)

We propose SAM-Road, an adaptation of the Segment Anything Model (SAM) for extracting large-scale, vectorized road network graphs from satellite imagery. To predict graph geometry, we formulate it as a dense semantic segmentation task, leveraging the inherent strengths of SAM. The image encoder of SAM is fine-tuned to produce probability masks for roads and intersections, from which the graph vertices are extracted via simple non-maximum suppression. To predict graph topology, we designed a lightweight transformer-based graph neural network, which leverages the SAM image embeddings to estimate the edge existence probabilities between vertices. Our approach directly predicts the graph vertices and edges for large regions without expensive and complex post-processing heuristics, and is capable of building complete road network graphs spanning multiple square kilometers in a matter of seconds. With its simple, straightforward, and minimalist design, SAM-Road achieves comparable accuracy with the state-of-the-art method RNGDet++, while being 40 times faster on the City-scale dataset. We thus demonstrate the power of a foundational vision model when applied to a graph learning task. The code is available at https://github.com/htcr/sam_road.