mlsanityData to 7 Oct 2026

CSGNet: Neural Shape Parser for Constructive Solid Geometry

arXiv 1712.08290 ↗First posted 22 Dec 2017cs.CV cs.AIcited by 106

Not on the map. Why?

Abstract (arXiv)

We present a neural architecture that takes as input a 2D or 3D shape and outputs a program that generates the shape. The instructions in our program are based on constructive solid geometry principles, i.e., a set of boolean operations on shape primitives defined recursively. Bottom-up techniques for this shape parsing task rely on primitive detection and are inherently slow since the search space over possible primitive combinations is large. In contrast, our model uses a recurrent neural network that parses the input shape in a top-down manner, which is significantly faster and yields a compact and easy-to-interpret sequence of modeling instructions. Our model is also more effective as a shape detector compared to existing state-of-the-art detection techniques. We finally demonstrate that our network can be trained on novel datasets without ground-truth program annotations through policy gradient techniques.

Key facts. Cited by 106 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 14; 2023: 16; 2024: 21; 2025: 15; 2026: 23.

106 papers.

Sort:

By area:

  1. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266
  2. 2022SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebookscited by 121
  3. 2023Hypothesis Search: Inductive Reasoning with Language Modelscited by 119
  4. 2021Im2Vec: Synthesizing Vector Graphics without Vector Supervisioncited by 114
  5. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  6. 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 101
  7. 2023Hierarchical Neural Coding for Controllable CAD Model Generationcited by 84
  8. 2022SolidGen: An Autoregressive Model for Direct B-rep Synthesiscited by 78
  9. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLMcited by 74
  10. 2021SketchGen: Generating Constrained CAD Sketchescited by 68
  11. 2021Vitruvion: A Generative Model of Parametric CAD Sketchescited by 66
  12. 2021CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assemblycited by 62
38 more
  1. 2024CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attentioncited by 62
  2. 2021Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinderscited by 59
  3. 2021CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsingcited by 51
  4. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  5. 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
  6. 2022Reconstructing editable prismatic CAD from rounded voxel modelscited by 41
  7. 2021ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generatorscited by 40
  8. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
  9. 2025CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generationcited by 39
  10. 2022ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsingcited by 38
  11. 2021HPNet: Deep Primitive Segmentation Using Hybrid Representationscited by 35
  12. 2024Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometrycited by 35
  13. 2024Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorizationcited by 34
  14. 2021PC2WF: 3D Wireframe Reconstruction from Raw Point Cloudscited by 33
  15. 2024Can Large Language Models Understand Symbolic Graphics Programs?cited by 32
  16. 2024The Scene Language: Representing Scenes with Programs, Words, and Embeddingscited by 31
  17. 2022CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representationscited by 30
  18. 2021Scene Synthesis via Uncertainty-Driven Attribute Synchronizationcited by 29
  19. 2025HoLa: B-Rep Generation using a Holistic Latent Representationcited by 29
  20. 2021CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Cloudscited by 24
  21. 2023ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitivescited by 22
  22. 2025TikZero: Zero-Shot Text-Guided Graphics Program Synthesiscited by 21
  23. 2022ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generationcited by 17
  24. 2025AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometrycited by 16
  25. 2021Hierarchical Motion Understanding via Motion Programscited by 14
  26. 2024PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformerscited by 14
  27. 2025cadrille: Multi-modal CAD Reconstruction with Reinforcement Learningcited by 14
  28. 2022From Perception to Programs: Regularize, Overparameterize, and Amortizecited by 13
  29. 2024NeurCADRecon: Neural Representation for Reconstructing CAD Surfaces by Enforcing Zero Gaussian Curvaturecited by 12
  30. 2025BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patchcited by 12
  31. 2023Improving Unsupervised Visual Program Inference with Code Rewriting Familiescited by 10
  32. 2024Diffusion On Syntax Trees For Program Synthesiscited by 10
  33. 2025VLMaterial: Procedural Material Generation with Large Vision-Language Modelscited by 9
  34. 2026Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selectioncited by 9
  35. 20263DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Codecited by 9
  36. 2024Learning to Edit Visual Programs with Self-Supervisioncited by 7
  37. 2024DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creationcited by 7
  38. 2025GenCAD-3D: CAD Program Generation using Multimodal Latent Space Alignment and Synthetic Dataset Balancingcited by 7

50 most cited of 106 All 106 (JSON)