mlsanityData to 7 Oct 2026

Geometric Deep Learning for Computer-Aided Design: A Survey

arXiv 2402.17695 ↗First posted 27 Feb 2024cs.CG cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Geometric Deep Learning techniques have become a transformative force in the field of Computer-Aided Design (CAD), and have the potential to revolutionize how designers and engineers approach and enhance the design process. By harnessing the power of machine learning-based methods, CAD designers can optimize their workflows, save time and effort while making better informed decisions, and create designs that are both innovative and practical. The ability to process the CAD designs represented by geometric data and to analyze their encoded features enables the identification of similarities among diverse CAD models, the proposition of alternative designs and enhancements, and even the generation of novel design alternatives. This survey offers a comprehensive overview of learning-based methods in computer-aided design across various categories, including similarity analysis and retrieval, 2D and 3D CAD model synthesis, and CAD generation from point clouds, and single/multi-view images. Additionally, it provides a complete list of benchmark datasets and their characteristics, along with open-source codes that have propelled research in this domain. The final discussion delves into the challenges prevalent in this field, followed by potential future research directions in this rapidly evolving field.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 57 of its 123 references that are in the map. First posted on arXiv 27 Feb 2024.

Builds on

57 of 123 references.

References · 57

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  10. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  11. 2015Pointer Networkscited by 882
  12. 2018Link Prediction Based on Graph Neural Networkscited by 829
38 more
  1. 2021How Attentive are Graph Attention Networks?cited by 818
  2. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  3. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  4. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  5. 2017A Neural Representation of Sketch Drawingscited by 311
  6. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  7. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266
  8. 2018Learning Deep Generative Models of Graphscited by 227
  9. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 182
  10. 2022SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebookscited by 121
  11. 2019Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapescited by 117
  12. 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 101
  13. 2017PCPNET: Learning Local Shape Properties from Raw Point Cloudscited by 97
  14. 2018MeshNet: Mesh Neural Network for 3D Shape Representationcited by 95
  15. 2021BRepNet: A topological message passing system for solid modelscited by 92
  16. 2019Molecular geometry prediction using a deep generative graph neural networkcited by 91
  17. 2018Supervised Fitting of Geometric Primitives to 3D Point Cloudscited by 90
  18. 2021Computer-Aided Design as Languagecited by 82
  19. 2022SolidGen: An Autoregressive Model for Direct B-rep Synthesiscited by 78
  20. 2021JoinABLe: Learning Bottom-up Assembly of Parametric CAD Jointscited by 77
  21. 2020SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Designcited by 72
  22. 2019IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Taskscited by 68
  23. 2021SketchGen: Generating Constrained CAD Sketchescited by 68
  24. 2021Vitruvion: A Generative Model of Parametric CAD Sketchescited by 66
  25. 2020Generative 3D Part Assembly via Dynamic Graph Learningcited by 65
  26. 20163D Shape Segmentation with Projective Convolutional Networkscited by 63
  27. 2021Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinderscited by 59
  28. 2021Inferring CAD Modeling Sequences Using Zone Graphscited by 50
  29. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  30. 2022Reconstructing editable prismatic CAD from rounded voxel modelscited by 41
  31. 2021RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assemblycited by 35
  32. 2020COALESCE: Component Assembly by Learning to Synthesize Connectionscited by 30
  33. 2022CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representationscited by 30
  34. 2022Self-Supervised Representation Learning for CADcited by 22
  35. 2022Neural Face Identification in a 2D Wireframe Projection of a Manifold Objectcited by 18
  36. 2019Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fitscited by 9
  37. 2020Progressive Spatio-Temporal Graph Convolutional Network for Skeleton-Based Human Action Recognitioncited by 9
  38. 2018Learning Material-Aware Local Descriptors for 3D Shapescited by 8

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 9.

14 papers.

Sort:

By area:

  1. 2025Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilitiescited by 43
  2. 2024Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomycited by 16
  3. 2026CADSmith: Multi-Agent CAD Generation with Programmatic Geometric Validationcited by 11
  4. 2024NeuroNURBS: Learning Efficient Surface Representations for 3D Solidscited by 8
  5. 2026Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Datacited by 7
  6. 2026Towards High-Fidelity CAD Generation via LLM-Driven Program Generation and Text-Based B-Rep Primitive Groundingcited by 6
  7. 2026BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoningcited by 3
  8. 2026FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Castingcited by 3
  9. 2025Recurrent U-Net-Based Graph Neural Network (RUGNN) for Accurate Deformation Predictions in Sheet Material Formingcited by 1
  10. 2026BRepCLIP: Contrastive Multimodal Pretraining on BRep Primitives for CAD Understandingcited by 1
  11. 2025Constructing a Neuro-Symbolic Mathematician from First Principlescited by 0
  12. 2026Kolmogorov-Arnold Networks-Based Tolerance-Aware Manufacturability Assessment Integrating Design-for-Manufacturing Principlescited by 0
2 more
  1. 2026Brep2Shape: Boundary and Shape Representation Alignment via Self-Supervised Transformerscited by 0
  2. 2026Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representationscited by 0