mlsanityData to 7 Oct 2026

DeepCAD: A Deep Generative Network for Computer-Aided Design Models

arXiv 2105.09492 ↗First posted 20 May 2021cs.CV cs.GR cs.LGcited by 266

Not on the map. Why?

Cited by 22 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Deep generative models of 3D shapes have received a great deal of research interest. Yet, almost all of them generate discrete shape representations, such as voxels, point clouds, and polygon meshes. We present the first 3D generative model for a drastically different shape representation --- describing a shape as a sequence of computer-aided design (CAD) operations. Unlike meshes and point clouds, CAD models encode the user creation process of 3D shapes, widely used in numerous industrial and engineering design tasks. However, the sequential and irregular structure of CAD operations poses significant challenges for existing 3D generative models. Drawing an analogy between CAD operations and natural language, we propose a CAD generative network based on the Transformer. We demonstrate the performance of our model for both shape autoencoding and random shape generation. To train our network, we create a new CAD dataset consisting of 178,238 models and their CAD construction sequences. We have made this dataset publicly available to promote future research on this topic.

Key facts. Cited by 266 papers in the map (data through 7 Oct 2026). Builds on 34 of its 51 references that are in the map. First posted on arXiv 20 May 2021.

Builds on

34 of 51 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  8. 2017Improved Training of Wasserstein GANscited by 2,223
  9. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  10. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  11. 2018Image Transformercited by 770
  12. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
22 more
  1. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  2. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  3. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  4. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  5. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  6. 2020Learning Gradient Fields for Shape Generationcited by 245
  7. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  8. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  9. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 158
  10. 2020SceneFormer: Indoor Scene Generation with Transformerscited by 154
  11. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 118
  12. 2017CSGNet: Neural Shape Parser for Constructive Solid Geometrycited by 106
  13. 2020ParSeNet: A Parametric Surface Fitting Network for 3D Point Cloudscited by 96
  14. 2021BRepNet: A topological message passing system for solid modelscited by 92
  15. 2021Computer-Aided Design as Languagecited by 82
  16. 2020UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Treecited by 77
  17. 2019Learning to Infer and Execute 3D Shape Programscited by 68
  18. 2020PIE-NET: Parametric Inference of Point Cloud Edgescited by 67
  19. 2019RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentationcited by 63
  20. 2021Inferring CAD Modeling Sequences Using Zone Graphscited by 50
  21. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  22. 2020UV-Net: Learning from Boundary Representationscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 14; 2023: 25; 2024: 43; 2025: 64; 2026: 116.

266 papers.

Sort:

By area:

  1. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  2. 2022SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebookscited by 121
  3. 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 101
  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. 2021JoinABLe: Learning Bottom-up Assembly of Parametric CAD Jointscited by 77
  8. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLMcited by 74
  9. 2021SketchGen: Generating Constrained CAD Sketchescited by 68
  10. 2021Vitruvion: A Generative Model of Parametric CAD Sketchescited by 66
  11. 2025CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generationcited by 65
  12. 2024CAD-Recode: Reverse Engineering CAD Code from Point Cloudscited by 63
38 more
  1. 2024CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attentioncited by 62
  2. 2024Generating CAD Code with Vision-Language Models for 3D Designscited by 61
  3. 2021Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinderscited by 59
  4. 2024CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMscited by 52
  5. 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
  6. 2025Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Modelscited by 43
  7. 2025Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilitiescited by 43
  8. 2022Reconstructing editable prismatic CAD from rounded voxel modelscited by 41
  9. 2023EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecastingcited by 41
  10. 2024CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solverscited by 40
  11. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
  12. 2025CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generationcited by 39
  13. 2022ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsingcited by 38
  14. 2024GenCAD: Image-Conditioned Computer-Aided Design Generation with Transformer-Based Contrastive Representation and Diffusion Priorscited by 36
  15. 2024Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometrycited by 35
  16. 2024Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorizationcited by 34
  17. 2024FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Modelscited by 33
  18. 2024Can Large Language Models Understand Symbolic Graphics Programs?cited by 32
  19. 2022Learning to Generate 3D Shapes from a Single Examplecited by 31
  20. 2025CADCrafter: Generating Computer-Aided Design Models from Unconstrained Imagescited by 31
  21. 2022CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representationscited by 30
  22. 2023Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shapecited by 29
  23. 2024TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Cloudscited by 29
  24. 2025HoLa: B-Rep Generation using a Holistic Latent Representationcited by 29
  25. 2024CadVLM: Bridging Language and Vision in the Generation of Parametric CAD Sketchescited by 28
  26. 2024OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Designcited by 26
  27. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  28. 2024Make-A-Shape: a Ten-Million-scale 3D Shape Modelcited by 25
  29. 2026Articraft: An Agentic System for Scalable Articulated 3D Asset Generationcited by 25
  30. 2025CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Designcited by 23
  31. 2022Self-Supervised Representation Learning for CADcited by 22
  32. 2023Category-Level Multi-Part Multi-Joint 3D Shape Assemblycited by 22
  33. 2023ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitivescited by 22
  34. 2024Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Promptscited by 22
  35. 2025CADDreamer: CAD Object Generation from Single-view Imagescited by 22
  36. 2025Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeekcited by 22
  37. 2024Large Language Model Agent as a Mechanical Designercited by 20
  38. 2025DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometrycited by 20

50 most cited of 266 All 266 (JSON)