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
Abstract
We present SkexGen, a novel autoregressive generative model for computer-aided design (CAD) construction sequences containing sketch-andextrude 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 .
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext facf8814-80e7-48db-bafb-6a462f910916Cited by top-tier papers42
- Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text PromptsMohammad Sadil Khan, Sankalp Sinha, Talha Uddin Sheikh, Didier Stricker et al.NeurIPS 2024 · 148 citations
- BrepGen: A B-rep Generative Diffusion Model with Structured Latent GeometryXiang Xu, Joseph G. Lambourne, Pradeep Kumar Jayaraman, Zhengqing Wang et al.SIGGRAPH 2024 · 62 citations
- D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and DropoutsFenggen Yu, Qimin Chen, Maham Tanveer, Ali Mahdavi-Amiri et al.NeurIPS 2023 · 61 citations
- CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMsSiyu Wang, Cailian Chen, Xinyi Le, Qimin Xu et al.AAAI 2025 · 49 citations
- Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeekXueyang Li, Jiahao Li, Yu Song, Yunzhong Lou et al.ICLR 2026 · 30 citations
Builds on11
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
- The Curious Case of Neural Text DegenerationAri Holtzman, Jan Buys, Li Du, Maxwell Forbes et al.ICLR 2020 · 4,112 citations
- DeepCAD: A Deep Generative Network for Computer-Aided Design ModelsRundi Wu, Chang Xiao, Changxi ZhengICCV 2021 · 290 citations
- Fusion 360 gallery: a dataset and environment for programmatic CAD construction from human design sequencesKarl D. D. Willis, Yewen Pu, Jieliang Luo, Hang Chu et al.SIGGRAPH 2021 · 197 citations
- UCSG-NET- Unsupervised Discovering of Constructive Solid Geometry TreeKacper Kania, Maciej Zieba, Tomasz KajdanowiczNeurIPS 2020 · 133 citations
Related papers
- Hierarchical Neural Coding for Controllable CAD Model GenerationXiang Xu, Pradeep Kumar Jayaraman, Joseph George Lambourne, Karl D. D. Willis et al.ICML 2023 · 88 citations
- SketchGen: Generating Constrained CAD SketchesWamiq Reyaz Para, Shariq Farooq Bhat, Paul Guerrero, Tom Kelly et al.NeurIPS 2021 · 114 citations
- Revisiting CAD Model Generation by Learning Raster SketchPu Li, Wenhao Zhang, Jianwei Guo, Jinglu Chen et al.AAAI 2025 · 7 citations
- CAD Translator: An Effective Drive for Text to 3D Parametric Computer-Aided Design Generative ModelingXueyang Li, Yu Song, Yunzhong Lou, Xiangdong ZhouACM MM 2024 · 16 citations
- MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric SequenceLiyuan Deng, Yunpeng Bai, Yongkang Dai, Xiaoshui Huang et al.ICCV 2025 · 3 citations
