Data-Driven Modeling for Chinese Ancient Architecture

Abstract

The existing 3D modeling studies of Chinese ancient architecture are mostly procedure driven and rely on fixed construction rules. Therefore, these methods have limited applications in virtual reality (VR) engineering. We propose a data-driven approach to synthesize 3D models from existing 3D data that provides more flexibility and fills the gap between academic studies and VR engineering. First, 3D architecture models were preprocessed and decomposed into components, and the components were clustered by their geometric features. Second, a Bayesian network was generated by learning from the dataset to represent the internal relationships between the architectural components. Third, the inference results of the trained network were utilized to generate a reasonable relationship matching to support the synthesis of the structural components. The proposed method can be used in 3D content creation for VR development and directly supports VR applications in practice.