# Neural Turtle Graphics for Modeling City Road Layouts

arXiv: https://arxiv.org/abs/1910.02055 · HTML: https://mlsanity.com/paper/1910.02055/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2019.

## Built on by (most cited first, 29 of 29)

- [Multimodal Motion Prediction with Stacked Transformers](https://mlsanity.com/paper/2103.11624/) (2021)
- [Relationformer: A Unified Framework for Image-to-Graph Generation](https://mlsanity.com/paper/2203.10202/) (2022)
- [Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction](https://mlsanity.com/paper/2303.08815/) (2023)
- [TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning](https://mlsanity.com/paper/2310.06753/) (2023)
- [HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps](https://mlsanity.com/paper/2106.14880/) (2021)
- [SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation](https://mlsanity.com/paper/2307.01646/) (2023)
- [Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments](https://mlsanity.com/paper/2503.22496/) (2025)
- [SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic](https://mlsanity.com/paper/2403.17933/) (2024)
- [CityGen: Infinite and Controllable City Layout Generation](https://mlsanity.com/paper/2312.01508/) (2023)
- [Lane Graph Estimation for Scene Understanding in Urban Driving](https://mlsanity.com/paper/2105.00195/) (2021)
- [Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving](https://mlsanity.com/paper/2109.01510/) (2021)
- [House-GAN++: Generative Adversarial Layout Refinement Networks](https://mlsanity.com/paper/2103.02574/) (2021)
- [Graph Representation Learning for Road Type Classification](https://mlsanity.com/paper/2107.07791/) (2021)
- [Pix2Map: Cross-modal Retrieval for Inferring Street Maps from Images](https://mlsanity.com/paper/2301.04224/) (2023)
- [Beyond Road Extraction: A Dataset for Map Update using Aerial Images](https://mlsanity.com/paper/2110.04690/) (2021)
- [GraphPNAS: Learning Distribution of Good Neural Architectures via Deep Graph Generative Models](https://mlsanity.com/paper/2211.15155/) (2022)
- [YOLinO: Generic Single Shot Polyline Detection in Real Time](https://mlsanity.com/paper/2103.14420/) (2021)
- [Updating Street Maps using Changes Detected in Satellite Imagery](https://mlsanity.com/paper/2110.06456/) (2021)
- [AutoEncoding Tree for City Generation and Applications](https://mlsanity.com/paper/2309.15941/) (2023)
- [Beyond Grid Data: Exploring Graph Neural Networks for Earth Observation](https://mlsanity.com/paper/2411.03223/) (2024)
- [Generative AI for Autonomous Driving: A Review](https://mlsanity.com/paper/2505.15863/) (2025)
- [Exact Recovery of Community Structures Using DeepWalk and Node2vec](https://mlsanity.com/paper/2101.07354/) (2021)
- [Large-Scale Auto-Regressive Modeling Of Street Networks](https://mlsanity.com/paper/2209.00281/) (2022)
- [RoBus: A Multimodal Dataset for Controllable Road Networks and Building Layouts Generation](https://mlsanity.com/paper/2407.07835/) (2024)
- [A Concise Survey on Lane Topology Reasoning for HD Mapping](https://mlsanity.com/paper/2504.01989/) (2025)
- [Mastering Spatial Graph Prediction of Road Networks](https://mlsanity.com/paper/2210.00828/) (2022)
- [ControlMap: Controllable High-Definition Map Generation for Traffic Scenario Simulation](https://mlsanity.com/paper/2606.15930/) (2026)
- [GANs for Urban Design](https://mlsanity.com/paper/2105.01727/) (2021)
- [DOGE: Differentiable Bezier Graph Optimization for Road Network Extraction](https://mlsanity.com/paper/2511.19850/) (2025)

## Abstract (arXiv)

We propose Neural Turtle Graphics (NTG), a novel generative model for spatial graphs, and demonstrate its applications in modeling city road layouts. Specifically, we represent the road layout using a graph where nodes in the graph represent control points and edges in the graph represent road segments. NTG is a sequential generative model parameterized by a neural network. It iteratively generates a new node and an edge connecting to an existing node conditioned on the current graph. We train NTG on Open Street Map data and show that it outperforms existing approaches using a set of diverse performance metrics. Moreover, our method allows users to control styles of generated road layouts mimicking existing cities as well as to sketch parts of the city road layout to be synthesized. In addition to synthesis, the proposed NTG finds uses in an analytical task of aerial road parsing. Experimental results show that it achieves state-of-the-art performance on the SpaceNet dataset.