# RoBus: A Multimodal Dataset for Controllable Road Networks and Building Layouts Generation

arXiv: https://arxiv.org/abs/2407.07835 · HTML: https://mlsanity.com/paper/2407.07835/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 50 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## Builds on (most cited first, 19 of 19)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving](https://mlsanity.com/paper/2304.14365/) (2023)
- [clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation](https://mlsanity.com/paper/2003.07311/) (2020)
- [LayoutDM: Discrete Diffusion Model for Controllable Layout Generation](https://mlsanity.com/paper/2303.08137/) (2023)
- [NetGAN: Generating Graphs via Random Walks](https://mlsanity.com/paper/1803.00816/) (2018)
- [LayoutVAE: Stochastic Scene Layout Generation From a Label Set](https://mlsanity.com/paper/1907.10719/) (2019)
- [House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation](https://mlsanity.com/paper/2003.06988/) (2020)
- [Constrained Graphic Layout Generation via Latent Optimization](https://mlsanity.com/paper/2108.00871/) (2021)
- [Neural Turtle Graphics for Modeling City Road Layouts](https://mlsanity.com/paper/1910.02055/) (2019)
- [Building-GAN: Graph-Conditioned Architectural Volumetric Design Generation](https://mlsanity.com/paper/2104.13316/) (2021)
- [A skeletonization algorithm for gradient-based optimization](https://mlsanity.com/paper/2309.02527/) (2023)
- [GlobalMapper: Arbitrary-Shaped Urban Layout Generation](https://mlsanity.com/paper/2307.09693/) (2023)
- ["An Adapt-or-Die Type of Situation": Perception, Adoption, and Use of Text-To-Image-Generation AI by Game Industry Professionals](https://mlsanity.com/paper/2302.12601/) (2023)
- [Modelling urban networks using Variational Autoencoders](https://mlsanity.com/paper/1905.06465/) (2019)
- [ReCo: A Dataset for Residential Community Layout Planning](https://mlsanity.com/paper/2206.04678/) (2022)
- [City Street Layout Generation via Conditional Adversarial Learning](https://mlsanity.com/paper/2305.08186/) (2023)
- [Incorporating planning intelligence into deep learning: A planning support tool for street network design](https://mlsanity.com/paper/2010.04536/) (2020)
- [Large-Scale Auto-Regressive Modeling Of Street Networks](https://mlsanity.com/paper/2209.00281/) (2022)

## Built on by (most cited first, 2 of 2)

- [Proc-GS: Procedural Building Generation for City Assembly with 3D Gaussians](https://mlsanity.com/paper/2412.07660/) (2024)
- [DiffRoad: Realistic and Diverse Road Scenario Generation for Autonomous Vehicle Testing](https://mlsanity.com/paper/2411.09451/) (2024)

## Abstract (arXiv)

Automated 3D city generation, focusing on road networks and building layouts, is in high demand for applications in urban design, multimedia games and autonomous driving simulations. The surge of generative AI facilitates designing city layouts based on deep learning models. However, the lack of high-quality datasets and benchmarks hinders the progress of these data-driven methods in generating road networks and building layouts. Furthermore, few studies consider urban characteristics, which generally take graphics as analysis objects and are crucial for practical applications, to control the generative process. To alleviate these problems, we introduce a multimodal dataset with accompanying evaluation metrics for controllable generation of Road networks and Building layouts (RoBus), which is the first and largest open-source dataset in city generation so far. RoBus dataset is formatted as images, graphics and texts, with 72,400 paired samples that cover around 80,000km2 globally. We analyze the RoBus dataset statistically and validate the effectiveness against existing road networks and building layouts generation methods. Additionally, we design new baselines that incorporate urban characteristics, such as road orientation and building density, in the process of generating road networks and building layouts using the RoBus dataset, enhancing the practicality of automated urban design. The RoBus dataset and related codes are published at https://github.com/tourlics/RoBusDataset.