mlsanityData to 7 Oct 2026

Reconstructing editable prismatic CAD from rounded voxel models

arXiv 2209.01161 ↗First posted 2 Sep 2022cs.CV cs.LGcited by 41

Not on the map. Why?

Abstract (arXiv)

Reverse Engineering a CAD shape from other representations is an important geometric processing step for many downstream applications. In this work, we introduce a novel neural network architecture to solve this challenging task and approximate a smoothed signed distance function with an editable, constrained, prismatic CAD model. During training, our method reconstructs the input geometry in the voxel space by decomposing the shape into a series of 2D profile images and 1D envelope functions. These can then be recombined in a differentiable way allowing a geometric loss function to be defined. During inference, we obtain the CAD data by first searching a database of 2D constrained sketches to find curves which approximate the profile images, then extrude them and use Boolean operations to build the final CAD model. Our method approximates the target shape more closely than other methods and outputs highly editable constrained parametric sketches which are compatible with existing CAD software.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 30 of its 54 references that are in the map. First posted on arXiv 2 Sep 2022.

Builds on

30 of 54 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  3. 2015Pointer Networkscited by 882
  4. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  5. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 302
  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. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  9. 2019CvxNet: Learnable Convex Decompositioncited by 173
  10. 2017CSGNet: Neural Shape Parser for Constructive Solid Geometrycited by 106
  11. 2020ParSeNet: A Parametric Surface Fitting Network for 3D Point Cloudscited by 96
  12. 2019Write, Execute, Assess: Program Synthesis with a REPLcited by 92
18 more
  1. 2018Supervised Fitting of Geometric Primitives to 3D Point Cloudscited by 90
  2. 2021Computer-Aided Design as Languagecited by 82
  3. 2022SolidGen: An Autoregressive Model for Direct B-rep Synthesiscited by 78
  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. 2021CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assemblycited by 62
  11. 2021Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinderscited by 59
  12. 2021Inferring CAD Modeling Sequences Using Zone Graphscited by 50
  13. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  14. 2021Joint Learning of 3D Shape Retrieval and Deformationcited by 41
  15. 2020Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequencescited by 36
  16. 2021HPNet: Deep Primitive Segmentation Using Hybrid Representationscited by 35
  17. 2020Deformation-Aware 3D Model Embedding and Retrievalcited by 30
  18. 2022ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generationcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 12; 2025: 11; 2026: 10.

41 papers.

Sort:

By area:

  1. 2023Hierarchical Neural Coding for Controllable CAD Model Generationcited by 84
  2. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLMcited by 74
  3. 2025CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generationcited by 65
  4. 2024CAD-Recode: Reverse Engineering CAD Code from Point Cloudscited by 63
  5. 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
  6. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
  7. 2024Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorizationcited by 34
  8. 2024TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Cloudscited by 29
  9. 2025HoLa: B-Rep Generation using a Holistic Latent Representationcited by 29
  10. 2024Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Promptscited by 22
  11. 2025CADDreamer: CAD Object Generation from Single-view Imagescited by 22
  12. 2025DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometrycited by 20
29 more
  1. 2023SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselinescited by 19
  2. 2024Split-and-Fit: Learning B-Reps via Structure-Aware Voronoi Partitioningcited by 17
  3. 2025AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometrycited by 16
  4. 2023Sketch-A-Shape: Zero-Shot Sketch-to-3D Shape Generationcited by 14
  5. 2024Geometric Deep Learning for Computer-Aided Design: A Surveycited by 14
  6. 2025cadrille: Multi-modal CAD Reconstruction with Reinforcement Learningcited by 14
  7. 2025BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patchcited by 12
  8. 2025Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawingscited by 9
  9. 2024NeuroNURBS: Learning Efficient Surface Representations for 3D Solidscited by 8
  10. 2024DiffCSG: Differentiable CSG via Rasterizationcited by 6
  11. 2024ContrastCAD: Contrastive Learning-based Representation Learning for Computer-Aided Design Modelscited by 5
  12. 2025MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scanscited by 4
  13. 2026CADReasoner: Iterative Program Editing for CAD Reverse Engineeringcited by 4
  14. 2023A Review of Deep Learning-Powered Mesh Reconstruction Methodscited by 3
  15. 2023A Survey of Methods for Converting Unstructured Data to CSG Modelscited by 3
  16. 2024MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Imagescited by 3
  17. 2026GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedbackcited by 3
  18. 2026CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimizationcited by 3
  19. 2026UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CADcited by 3
  20. 2025Target-Guided Bayesian Flow Networks for Quantitatively Constrained CAD Generationcited by 2
  21. 2026Autoregressive B-Rep Shape Generation with Parametric Surfacescited by 2
  22. 2023P2CADNet: An End-to-End Reconstruction Network for Parametric 3D CAD Model from Point Cloudscited by 1
  23. 2024PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstructioncited by 1
  24. 2025CADMorph: Geometry-Driven Parametric CAD Editing via a Plan-Generate-Verify Loopcited by 0
  25. 2026Flatten The Complex: Joint B-Rep Generation via Compositional k-Cell Particlescited by 0
  26. 2026PLLM: Pseudo-Labeling Large Language Models for CAD Program Synthesiscited by 0
  27. 2026A2Z-10M+: Geometric Deep Learning with A-to-Z BRep Annotations for AI-Assisted CAD Modeling and Reverse Engineeringcited by 0
  28. 2026Agent-Aided Design for Dynamic CAD Modelscited by 0
  29. 2026GuideCAD: A Lightweight Multimodal Framework for 3D CAD Model Generation via Prefix Embeddingcited by 0