# Image-Conditioned Graph Generation for Road Network Extraction

arXiv: https://arxiv.org/abs/1910.14388 · HTML: https://mlsanity.com/paper/1910.14388/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2019.

## Built on by (most cited first, 17 of 17)

- [Relationformer: A Unified Framework for Image-to-Graph Generation](https://mlsanity.com/paper/2203.10202/) (2022)
- [RNGDet: Road Network Graph Detection by Transformer in Aerial Images](https://mlsanity.com/paper/2202.07824/) (2022)
- [Iterative Scene Graph Generation with Generative Transformers](https://mlsanity.com/paper/2211.16636/) (2022)
- [iCurb: Imitation Learning-based Detection of Road Curbs using Aerial Images for Autonomous Driving](https://mlsanity.com/paper/2103.17118/) (2021)
- [Topo-boundary: A Benchmark Dataset on Topological Road-boundary Detection Using Aerial Images for Autonomous Driving](https://mlsanity.com/paper/2103.17119/) (2021)
- [Brain Multigraph Prediction using Topology-Aware Adversarial Graph Neural Network](https://mlsanity.com/paper/2105.02565/) (2021)
- [Let There Be Order: Rethinking Ordering in Autoregressive Graph Generation](https://mlsanity.com/paper/2305.15562/) (2023)
- [Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss](https://mlsanity.com/paper/2402.12269/) (2024)
- [From Engineering Diagrams to Graphs: Digitizing P&IDs with Transformers](https://mlsanity.com/paper/2411.13929/) (2024)
- [Hierarchical Part-based Generative Model for Realistic 3D Blood Vessel](https://mlsanity.com/paper/2507.15223/) (2025)
- [HoliTracer: Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery](https://mlsanity.com/paper/2507.16251/) (2025)
- [Self-Labeling of Fully Mediating Representations by Graph Alignment](https://mlsanity.com/paper/2103.14133/) (2021)
- [LIC-GAN: Language Information Conditioned Graph Generative GAN Model](https://mlsanity.com/paper/2306.01937/) (2023)
- [Cross-domain and Cross-dimension Learning for Image-to-Graph Transformers](https://mlsanity.com/paper/2403.06601/) (2024)
- [TreeFormer: Single-view Plant Skeleton Estimation via Tree-constrained Graph Generation](https://mlsanity.com/paper/2411.16132/) (2024)
- [Knowledge Generation -- Variational Bayes on Knowledge Graphs](https://mlsanity.com/paper/2101.08857/) (2021)
- [VisAdj: Learning Adjacency Matrices from Node-Link Images](https://mlsanity.com/paper/2608.21825/) (2026)

## Abstract (arXiv)

Deep generative models for graphs have shown great promise in the area of drug design, but have so far found little application beyond generating graph-structured molecules. In this work, we demonstrate a proof of concept for the challenging task of road network extraction from image data. This task can be framed as image-conditioned graph generation, for which we develop the Generative Graph Transformer (GGT), a deep autoregressive model that makes use of attention mechanisms for image conditioning and the recurrent generation of graphs. We benchmark GGT on the application of road network extraction from semantic segmentation data. For this, we introduce the Toulouse Road Network dataset, based on real-world publicly-available data. We further propose the StreetMover distance: a metric based on the Sinkhorn distance for effectively evaluating the quality of road network generation. The code and dataset are publicly available.