mlsanityData to 7 Oct 2026

Computer-Aided Design as Language

arXiv 2105.02769 ↗First posted 6 May 2021cs.CV cs.LGcited by 82

Not on the map. Why?

Abstract (arXiv)

Computer-Aided Design (CAD) applications are used in manufacturing to model everything from coffee mugs to sports cars. These programs are complex and require years of training and experience to master. A component of all CAD models particularly difficult to make are the highly structured 2D sketches that lie at the heart of every 3D construction. In this work, we propose a machine learning model capable of automatically generating such sketches. Through this, we pave the way for developing intelligent tools that would help engineers create better designs with less effort. Our method is a combination of a general-purpose language modeling technique alongside an off-the-shelf data serialization protocol. We show that our approach has enough flexibility to accommodate the complexity of the domain and performs well for both unconditional synthesis and image-to-sketch translation.

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). Builds on 21 of its 60 references that are in the map. First posted on arXiv 6 May 2021.

Builds on

21 of 60 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  6. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  7. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  8. 2015Pointer Networkscited by 882
  9. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  10. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
  11. 2013Generating Sequences With Recurrent Neural Networkscited by 549
  12. 2020Jukebox: A Generative Model for Musiccited by 535
9 more
  1. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  2. 2017A Neural Representation of Sketch Drawingscited by 311
  3. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  4. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 158
  5. 2021Im2Vec: Synthesizing Vector Graphics without Vector Supervisioncited by 114
  6. 2018Synthesizing Programs for Images using Reinforced Adversarial Learningcited by 72
  7. 2020SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Designcited by 72
  8. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  9. 2020Deep Vectorization of Technical Drawingscited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 13; 2023: 10; 2024: 24; 2025: 16; 2026: 13.

82 papers.

Sort:

By area:

  1. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266
  2. 2022VectorMapNet: End-to-end Vectorized HD Map Learningcited by 243
  3. 2022SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebookscited by 121
  4. 2024SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Modelcited by 95
  5. 2023Hierarchical Neural Coding for Controllable CAD Model Generationcited by 84
  6. 2022SolidGen: An Autoregressive Model for Direct B-rep Synthesiscited by 78
  7. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLMcited by 74
  8. 2021SketchGen: Generating Constrained CAD Sketchescited by 68
  9. 2021Vitruvion: A Generative Model of Parametric CAD Sketchescited by 66
  10. 2024CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attentioncited by 62
  11. 2021Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinderscited by 59
  12. 2022Reconstructing editable prismatic CAD from rounded voxel modelscited by 41
38 more
  1. 2022ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsingcited by 38
  2. 2024Graphic Design with Large Multimodal Modelcited by 38
  3. 2024GenCAD: Image-Conditioned Computer-Aided Design Generation with Transformer-Based Contrastive Representation and Diffusion Priorscited by 36
  4. 2024Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorizationcited by 34
  5. 2024FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Modelscited by 33
  6. 2022CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representationscited by 30
  7. 2024SketchAgent: Language-Driven Sequential Sketch Generationcited by 30
  8. 2024CadVLM: Bridging Language and Vision in the Generation of Parametric CAD Sketchescited by 28
  9. 2024OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Designcited by 26
  10. 2024A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directionscited by 24
  11. 2022Self-Supervised Representation Learning for CADcited by 22
  12. 2023ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitivescited by 22
  13. 2024Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Promptscited by 22
  14. 2025Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeekcited by 22
  15. 2022ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generationcited by 17
  16. 2024From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approachcited by 15
  17. 2022Abstracting Sketches through Simple Primitivescited by 14
  18. 2024Geometric Deep Learning for Computer-Aided Design: A Surveycited by 14
  19. 2025BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patchcited by 12
  20. 2021Recognizing Vector Graphics without Rasterizationcited by 11
  21. 2022Discovering Design Concepts for CAD Sketchescited by 10
  22. 2024PICASSO: A Feed-Forward Framework for Parametric Inference of CAD Sketches via Rendering Self-Supervisioncited by 9
  23. 2023PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programscited by 8
  24. 2025Aligning Constraint Generation with Design Intent in Parametric CADcited by 8
  25. 2025CAD-Coder:Text-Guided CAD Files Code Generationcited by 8
  26. 2024Parametric Primitive Analysis of CAD Sketches with Vision Transformercited by 7
  27. 2024DAVINCI: A Single-Stage Architecture for Constrained CAD Sketch Inferencecited by 6
  28. 2025Revisiting CAD Model Generation by Learning Raster Sketchcited by 6
  29. 2023Architext: Language-Driven Generative Architecture Designcited by 5
  30. 2024SketchGPT: Autoregressive Modeling for Sketch Generation and Recognitioncited by 5
  31. 2025SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generationcited by 5
  32. 2025Human-in-the-Loop Local Corrections of 3D Scene Layouts via Infillingcited by 4
  33. 2025GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Modelscited by 4
  34. 2025MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scanscited by 4
  35. 2021Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interfacecited by 3
  36. 2023A Survey of Methods for Converting Unstructured Data to CSG Modelscited by 3
  37. 2024Robust Shape Fitting for 3D Scene Abstractioncited by 3
  38. 2024MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Imagescited by 3

50 most cited of 82 All 82 (JSON)