Creation of Virtual City 3D Model for EM-Wave Propagation Dataset Extension

In this paper, we propose a method to generate a 3D model of virtual cities for propagation data generation by ray tracing. When creating propagation estimation models using machine learning, propagation data created by simulations such as ray tracing may be used as training data. In this case, 3D models of the propagation environment is necessary, but there is a limit to the amount of 3D models that can be created based on real cities, and there is a possibility that a sufficient amount of data may not be available for model training. Therefore, the objective of this study is to generate a map of naturally occurring building layouts using an image generation model, and to create a 3D model on the basis of this map to ensure a larger number of practical propagation environment models.