SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks
Abstract
We present SkexGen, a novel autoregressive generative model for computer-aided design (CAD) construction sequences containing sketch-and-extrude modeling operations. Our model utilizes distinct Transformer architectures to encode topological, geometric, and extrusion variations of construction sequences into disentangled codebooks. Autoregressive Transformer decoders generate CAD construction sequences sharing certain properties specified by the codebook vectors. Extensive experiments demonstrate that our disentangled codebook representation generates diverse and high-quality CAD models, enhances user control, and enables efficient exploration of the design space. The code is available at https://samxuxiang.github.io/skexgen.
Cite
Text
Xu et al. "SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks." International Conference on Machine Learning, 2022.Markdown
[Xu et al. "SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks." International Conference on Machine Learning, 2022.](https://mlanthology.org/icml/2022/xu2022icml-skexgen/)BibTeX
@inproceedings{xu2022icml-skexgen,
title = {{SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks}},
author = {Xu, Xiang and Willis, Karl D.D. and Lambourne, Joseph G and Cheng, Chin-Yi and Jayaraman, Pradeep Kumar and Furukawa, Yasutaka},
booktitle = {International Conference on Machine Learning},
year = {2022},
pages = {24698-24724},
volume = {162},
url = {https://mlanthology.org/icml/2022/xu2022icml-skexgen/}
}