A novel transformer‐based graph generation model for vectorized road design

• Published in: Computer animation and virtual worlds Vol. 35; no. 3
• Main Authors: Zhou, Peichi, Li, Chen, Zhang, Jian, Wang, Changbo, Qin, Hong, Liu, Long
• Format: Journal Article
• Language: English
• Published: Chichester Wiley Subscription Services, Inc 01.05.2024
• Subjects: Computer & video games; generative model; Graphs; Image processing; landscape modeling; Modelling; Network design; non‐urban road network; Road design; Vegetation mapping
• ISSN: 1546-4261; 1546-427X
• DOI: 10.1002/cav.2267

Road network design, as an important part of landscape modeling, shows a great significance in automatic driving, video game development, and disaster simulation. To date, this task remains labor‐intensive, tedious and time‐consuming. Many improved techniques have been proposed during the last two decades. Nevertheless, most of the state‐of‐the‐art methods still encounter problems of intuitiveness, usefulness and/or interactivity. As a rapid deviation from the conventional road design, this paper advocates an improved road modeling framework for automatic and interactive road production driven by geographical maps (including elevation, water, vegetation maps). Our method integrates the capability of flexible image generation models with powerful transformer architecture to afford a vectorized road network. We firstly construct a dataset that includes road graphs, density map and their corresponding geographical maps. Secondly, we develop a density map generation network based on image translation model with an attention mechanism to predict a road density map. The usage of density map facilitates faster convergence and better performance, which also serves as the input for road graph generation. Thirdly, we employ the transformer architecture to evolve density maps to road graphs. Our comprehensive experimental results have verified the efficiency, robustness and applicability of our newly‐proposed framework for road design. The input to our framework is geographical maps. The density map generation network can generate density maps based on these inputs, and finally the graph generation network can generate road graphs based on the generated density maps.