Publication | International Conference on Machine Learning 2022

SkexGen

Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks

This Autodesk Research paper describes a new approach to generation of solid CAD models that enhances user control and enables efficient exploration of the design space.

Download publication

Abstract

SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks

Xiang Xu, Karl D.D. Willis, Joseph G. Lambourne, Chin-Yi Cheng, Pradeep Kumar Jayaraman, Yasutaka Furukawa

International Conference on Machine Learning 2022

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.

Associated Researchers

Chin-Yi Cheng

Autodesk Research

Xiang Xu

Simon Fraser University

Yasutaka Furukawa

Simon Fraser University

View all researchers

Related Resources

Publication

2023

Language Model Crossover: Variation through Few-Shot Prompting

Pursuing the insight that language models naturally enable an…

Publication

2023

CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation

Generating shapes using natural language can enable new ways of…

Publication

2019

Dynamic Experience Replay

We present a novel technique called Dynamic Experience Replay (DER)…

Project

2022

Systems Design and Simulation

Predictive models of complex systems will require a more scalable,…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us