Style Classification and Generation of Furniture Design Styles: A Method Based on Generative Adversarial Networks

Abstract

The purpose of this study is to provide a new method for the classification and generation of furniture design styles through the integration of DL (Deep Learning) and CAD technology. The introduction part expounds on the development status of the furniture design industry, makes it clear that the goal of this study is to provide a new method for the classification and generation of furniture design styles, and points out the potential value and influence of this method on the furniture design industry. Then, the data set preparation, DL model construction, and CAD integration method are described in detail. The experiment and simulation part shows the experimental environment, steps, and results. The results show that the model not only performs well on the training data but also has good generalization ability and can deal with unknown data. At the same time, after integrating the DL model with CAD software, users' scores on the diversity and innovation of furniture design styles have been significantly improved. It proves the effectiveness of this research method in the classification and generation of furniture design styles. It is concluded that the method proposed in this study has high accuracy and practicability in the classification and generation of furniture design styles and provides a new idea for the intelligent and automatic development of the furniture design industry.