mlsanityData to 13 Oct 2026

Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders

arXiv 2112.09329 ↗First posted 17 Dec 2021cs.CVcited by 60

Not on the map. Why?

Abstract (arXiv)

We propose Point2Cyl, a supervised network transforming a raw 3D point cloud to a set of extrusion cylinders. Reverse engineering from a raw geometry to a CAD model is an essential task to enable manipulation of the 3D data in shape editing software and thus expand their usages in many downstream applications. Particularly, the form of CAD models having a sequence of extrusion cylinders -- a 2D sketch plus an extrusion axis and range -- and their boolean combinations is not only widely used in the CAD community/software but also has great expressivity of shapes, compared to having limited types of primitives (e.g., planes, spheres, and cylinders). In this work, we introduce a neural network that solves the extrusion cylinder decomposition problem in a geometry-grounded way by first learning underlying geometric proxies. Precisely, our approach first predicts per-point segmentation, base/barrel labels and normals, then estimates for the underlying extrusion parameters in differentiable and closed-form formulations. Our experiments show that our approach demonstrates the best performance on two recent CAD datasets, Fusion Gallery and DeepCAD, and we further showcase our approach on reverse engineering and editing.

Key facts. Cited by 60 papers in the map (data through 13 Oct 2026). Builds on 30 of its 61 references that are in the map. First posted on arXiv 17 Dec 2021.

Builds on

30 of 61 references.

References · 30

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,231
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,389
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,686
  4. 2020Implicit Geometric Regularization for Learning Shapescited by 708
  5. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  6. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  7. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 341
  8. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  9. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 270
  10. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 124
  11. 2017CSGNet: Neural Shape Parser for Constructive Solid Geometrycited by 106
  12. 2020ParSeNet: A Parametric Surface Fitting Network for 3D Point Cloudscited by 96
18 more
  1. 2021BRepNet: A topological message passing system for solid modelscited by 92
  2. 2018Supervised Fitting of Geometric Primitives to 3D Point Cloudscited by 91
  3. 2021Computer-Aided Design as Languagecited by 82
  4. 2020UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Treecited by 77
  5. 2020SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Designcited by 72
  6. 2019Learning to Infer and Execute 3D Shape Programscited by 68
  7. 2021SketchGen: Generating Constrained CAD Sketchescited by 68
  8. 2020PIE-NET: Parametric Inference of Point Cloud Edgescited by 67
  9. 2021Vitruvion: A Generative Model of Parametric CAD Sketchescited by 66
  10. 2021CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsingcited by 51
  11. 2021Inferring CAD Modeling Sequences Using Zone Graphscited by 50
  12. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  13. 2020Deformation-Aware 3D Model Embedding and Retrievalcited by 30
  14. 2021CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Cloudscited by 24
  15. 2019Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fitscited by 9
  16. 2020From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Cloudscited by 7
  17. 2018A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Cloudscited by 4
  18. 2020PrimiTect: Fast Continuous Hough Voting for Primitive Detectioncited by 3

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 5; 2023: 10; 2024: 16; 2025: 12; 2026: 17.

60 papers.

Sort:

By area:

  1. 2023Hierarchical Neural Coding for Controllable CAD Model Generationcited by 86
  2. 2022SolidGen: An Autoregressive Model for Direct B-rep Synthesiscited by 80
  3. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLMcited by 78
  4. 2025CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generationcited by 66
  5. 2024CAD-Recode: Reverse Engineering CAD Code from Point Cloudscited by 65
  6. 2024CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attentioncited by 63
  7. 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
  8. 2022Reconstructing editable prismatic CAD from rounded voxel modelscited by 41
  9. 2024CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solverscited by 40
  10. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
  11. 2023Point2CAD: Reverse Engineering CAD Models from 3D Point Cloudscited by 36
  12. 2024Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorizationcited by 34
38 more
  1. 2022CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representationscited by 30
  2. 2025HoLa: B-Rep Generation using a Holistic Latent Representationcited by 30
  3. 2024TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Cloudscited by 29
  4. 2024OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Designcited by 26
  5. 2025CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Designcited by 24
  6. 2025DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometrycited by 21
  7. 2023SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselinescited by 19
  8. 2024Geometric Deep Learning for Computer-Aided Design: A Surveycited by 14
  9. 2025BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patchcited by 13
  10. 2024NeurCADRecon: Neural Representation for Reconstructing CAD Surfaces by Enforcing Zero Gaussian Curvaturecited by 12
  11. 2026Text-to-CAD Evaluation with CADTestscited by 10
  12. 2026CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generationcited by 10
  13. 2025VLMaterial: Procedural Material Generation with Large Vision-Language Modelscited by 9
  14. 2025GenCAD-3D: CAD Program Generation using Multimodal Latent Space Alignment and Synthetic Dataset Balancingcited by 8
  15. 2024Parametric Primitive Analysis of CAD Sketches with Vision Transformercited by 7
  16. 2025CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generationcited by 6
  17. 2022Vitruvio: 3D Building Meshes via Single Perspective Sketchescited by 5
  18. 2024SweepNet: Unsupervised Learning Shape Abstraction via Neural Sweeperscited by 5
  19. 2025MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scanscited by 5
  20. 2023Recognising geometric primitives in 3D point clouds of mechanical CAD objectscited by 4
  21. 2024BRep Boundary and Junction Detection for CAD Reverse Engineeringcited by 4
  22. 2025Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Predictioncited by 4
  23. 2026CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimizationcited by 4
  24. 2023A Review of Deep Learning-Powered Mesh Reconstruction Methodscited by 3
  25. 2023A Survey of Methods for Converting Unstructured Data to CSG Modelscited by 3
  26. 2024Robust Shape Fitting for 3D Scene Abstractioncited by 3
  27. 2024MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Imagescited by 3
  28. 2026Mamba-CAD: State Space Model For 3D Computer-Aided Design Generative Modelingcited by 3
  29. 2026GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedbackcited by 3
  30. 2026UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CADcited by 3
  31. 2023QuadricsNet: Learning Concise Representation for Geometric Primitives in Point Cloudscited by 2
  32. 2023PPI-NET: End-to-End Parametric Primitive Inferencecited by 1
  33. 2024Improved Convex Decomposition with Ensembling and Negative Primitivescited by 1
  34. 2024Constraint-Aware Feature Learning for Parametric Point Cloudcited by 1
  35. 2025Joint Neural SDF Reconstruction and Semantic Segmentation for CAD Modelscited by 1
  36. 2026PLLM: Pseudo-Labeling Large Language Models for CAD Program Synthesiscited by 1
  37. 2026DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfacescited by 1
  38. 2026HierCAD: Hierarchical Text-to-CAD Design via Structure Alignment and Parameter Groundingcited by 1

50 most cited of 60 All 60 (JSON)