mlsanityData to 7 Oct 2026

Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts

arXiv 2409.17106 ↗First posted 25 Sep 2024cs.CV cs.GRcited by 22

Not on the map. Why?

Abstract (arXiv)

Prototyping complex computer-aided design (CAD) models in modern softwares can be very time-consuming. This is due to the lack of intelligent systems that can quickly generate simpler intermediate parts. We propose Text2CAD, the first AI framework for generating text-to-parametric CAD models using designer-friendly instructions for all skill levels. Furthermore, we introduce a data annotation pipeline for generating text prompts based on natural language instructions for the DeepCAD dataset using Mistral and LLaVA-NeXT. The dataset contains ~170K models and ~660K text annotations, from abstract CAD descriptions (e.g., generate two concentric cylinders) to detailed specifications (e.g., draw two circles with center (x,y) and radius r1, r2, and extrude along the normal by d...). Within the Text2CAD framework, we propose an end-to-end transformer-based auto-regressive network to generate parametric CAD models from input texts. We evaluate the performance of our model through a mixture of metrics, including visual quality, parametric precision, and geometrical accuracy. Our proposed framework shows great potential in AI-aided design applications. Our source code and annotations will be publicly available.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 39 of its 55 references that are in the map. First posted on arXiv 25 Sep 2024.

Builds on

39 of 55 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2023GPT-4 Technical Reportcited by 18,132
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  7. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  8. 2023Visual Instruction Tuningcited by 7,792
  9. 2023Mistral 7Bcited by 3,065
  10. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  11. 2024Mixtral of Expertscited by 1,785
  12. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
27 more
  1. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  2. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  3. 2015Pointer Networkscited by 882
  4. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  5. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  6. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  7. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  8. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266
  9. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 182
  10. 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generationcited by 151
  11. 2022SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebookscited by 121
  12. 2023GPT-4V(ision) as a Generalist Evaluator for Vision-Language Taskscited by 118
  13. 2021BRepNet: A topological message passing system for solid modelscited by 92
  14. 2023Hierarchical Neural Coding for Controllable CAD Model Generationcited by 84
  15. 2021Computer-Aided Design as Languagecited by 82
  16. 2020SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Designcited by 72
  17. 2021SketchGen: Generating Constrained CAD Sketchescited by 68
  18. 2021Vitruvion: A Generative Model of Parametric CAD Sketchescited by 66
  19. 2024CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attentioncited by 62
  20. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  21. 2022CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Languagecited by 46
  22. 2022Reconstructing editable prismatic CAD from rounded voxel modelscited by 41
  23. 2022CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representationscited by 30
  24. 2023Neurosymbolic Models for Computer Graphicscited by 27
  25. 2021PvDeConv: Point-Voxel Deconvolution for Autoencoding CAD Construction in 3Dcited by 20
  26. 2023SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselinescited by 19
  27. 2024ContrastCAD: Contrastive Learning-based Representation Learning for Computer-Aided Design Modelscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 8; 2026: 11.

22 papers.

Sort:

By area:

  1. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLMcited by 74
  2. 2025CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generationcited by 65
  3. 2025Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Modelscited by 43
  4. 2025Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilitiescited by 43
  5. 2025CADCrafter: Generating Computer-Aided Design Models from Unconstrained Imagescited by 31
  6. 2025BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patchcited by 12
  7. 2026CADSmith: Multi-Agent CAD Generation with Programmatic Geometric Validationcited by 11
  8. 2026BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CADcited by 11
  9. 2026Text2CAD-Bench: A Benchmark for LLM-based Text-to-Parametric CAD Generationcited by 11
  10. 2025MoVer: Motion Verification for Motion Graphics Animationscited by 10
  11. 2025GarmentDiffusion: 3D Garment Sewing Pattern Generation with Multimodal Diffusion Transformerscited by 9
  12. 2026MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generationcited by 8
10 more
  1. 2024MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creationcited by 7
  2. 2024Don't Mesh with Me: Generating Constructive Solid Geometry Instead of Meshes by Fine-Tuning a Code-Generation LLMcited by 6
  3. 2025RLCAD: Reinforcement Learning Training Gym for Revolution Involved CAD Command Sequence Generationcited by 6
  4. 2026Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Designcited by 3
  5. 2026CADEngBench: It Looks Like CAD, but Does It Work? Evaluating Parametric Design, Assembly Reasoning, and Physics Simulationcited by 3
  6. 2026SldprtNet: A Large-Scale Multimodal Dataset for CAD Generation in Language-Driven 3D Designcited by 2
  7. 2026Nova3D: Code-Native Generation of Programmable 3D Assetscited by 1
  8. 2026CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Designcited by 1
  9. 2026LLM-based Visual Code Completion for Aerospace Geometric Designcited by 0
  10. 2026AgenticCADedit: A Stateful, Tool-Mediated Agentic Approach to Multimodal 3D CAD Editingcited by 0