Poster
SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks
Xiang Xu · Karl Willis · Joseph G Lambourne · Chin-Yi Cheng · Pradeep Kumar Jayaraman · Yasutaka Furukawa
Hall E #314
Keywords: [ APP: Computer Vision ] [ DL: Sequential Models, Time series ] [ DL: Generative Models and Autoencoders ]
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.