| Title |
Generating 3D CAD Models using a Transformer Autoencoders and a Diffusion Model |
| Authors |
정민섭(Minseop Jung) ; 김민성(Minseong Kim) ; 김지범(Jibum Kim) |
| DOI |
https://doi.org/10.5573/ieie.2023.60.12.25 |
| Keywords |
CAD; Deep learning; Transformer; Diffusion model; Autoencoder |
| Abstract |
In this paper, we propose a novel deep learning model that generates 3D CAD models represented as command sequences. The proposed model consists of a transformer-based autoencoder and a diffusion-based generative model. The transformer-based autoencoder learns latent representations to generate CAD command sequences effectively, and the diffusion-based generative model learns to generate latent variables for creating new command sequences. Experimental results show that the proposed model is able to successfully generate valid and new 3D CAD models. Our experiments also show that the proposed model learns the meaningful latent space for CAD models. |