mlsanityData to 7 Oct 2026

CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

arXiv 2108.11305 ↗First posted 25 Aug 2021cs.CV cs.GR cs.LGcited by 51

Not on the map. Why?

Abstract (arXiv)

Generating an interpretable and compact representation of 3D shapes from point clouds is an important and challenging problem. This paper presents CSG-Stump Net, an unsupervised end-to-end network for learning shapes from point clouds and discovering the underlying constituent modeling primitives and operations as well. At the core is a three-level structure called em CSG-Stump, consisting of a complement layer at the bottom, an intersection layer in the middle, and a union layer at the top. CSG-Stump is proven to be equivalent to CSG in terms of representation, therefore inheriting the interpretable, compact and editable nature of CSG while freeing from CSG's complex tree structures. Particularly, the CSG-Stump has a simple and regular structure, allowing neural networks to give outputs of a constant dimensionality, which makes itself deep-learning friendly. Due to these characteristics of CSG-Stump, CSG-Stump Net achieves superior results compared to previous CSG-based methods and generates much more appealing shapes, as confirmed by extensive experiments. Project page: https://kimren227.github.io/projects/CSGStump/

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 25 of its 37 references that are in the map. First posted on arXiv 25 Aug 2021.

Builds on

25 of 37 references.

References · 25

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  9. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  10. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  11. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  12. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
13 more
  1. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  2. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  3. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  4. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  5. 2019CvxNet: Learnable Convex Decompositioncited by 173
  6. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  7. 2017CSGNet: Neural Shape Parser for Constructive Solid Geometrycited by 106
  8. 2019Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformationcited by 103
  9. 2018Supervised Fitting of Geometric Primitives to 3D Point Cloudscited by 90
  10. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  11. 2020DualSDF: Semantic Shape Manipulation using a Two-Level Representationcited by 82
  12. 2020UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Treecited by 77
  13. 2017Image2Mesh: A Learning Framework for Single Image 3D Reconstructioncited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 9; 2024: 18; 2025: 9; 2026: 9.

51 papers.

Sort:

By area:

  1. 2022Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generationcited by 119
  2. 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 101
  3. 2023Hierarchical Neural Coding for Controllable CAD Model Generationcited by 84
  4. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLMcited by 74
  5. 2021Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinderscited by 59
  6. 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
  7. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
  8. 2022ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsingcited by 38
  9. 2024Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometrycited by 35
  10. 2024Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorizationcited by 34
  11. 2024FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Modelscited by 33
  12. 2025HoLa: B-Rep Generation using a Holistic Latent Representationcited by 29
38 more
  1. 2023ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitivescited by 22
  2. 2022ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generationcited by 17
  3. 2025cadrille: Multi-modal CAD Reconstruction with Reinforcement Learningcited by 14
  4. 2025BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patchcited by 12
  5. 2023Improving Unsupervised Visual Program Inference with Code Rewriting Familiescited by 10
  6. 2024Text2CAD: Text to 3D CAD Generation via Technical Drawingscited by 9
  7. 2026Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selectioncited by 9
  8. 2024Learning to Edit Visual Programs with Self-Supervisioncited by 7
  9. 2024DiffCSG: Differentiable CSG via Rasterizationcited by 6
  10. 2024Don't Mesh with Me: Generating Constructive Solid Geometry Instead of Meshes by Fine-Tuning a Code-Generation LLMcited by 6
  11. 2025Revisiting CAD Model Generation by Learning Raster Sketchcited by 6
  12. 2025Parametric Point Cloud Completion for Polygonal Surface Reconstructioncited by 6
  13. 2024DPA-Net: Structured 3D Abstraction from Sparse Views via Differentiable Primitive Assemblycited by 5
  14. 2024SweepNet: Unsupervised Learning Shape Abstraction via Neural Sweeperscited by 5
  15. 2025ShapeLib: Designing a library of programmatic 3D shape abstractions with Large Language Modelscited by 5
  16. 2022Implicit Conversion of Manifold B-Rep Solids by Neural Halfspace Representationcited by 4
  17. 2024Concise Plane Arrangements for Low-Poly Surface and Volume Modellingcited by 4
  18. 2025Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Predictioncited by 4
  19. 2025MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scanscited by 4
  20. 2026CADReasoner: Iterative Program Editing for CAD Reverse Engineeringcited by 4
  21. 2023A Review of Deep Learning-Powered Mesh Reconstruction Methodscited by 3
  22. 2023A Survey of Methods for Converting Unstructured Data to CSG Modelscited by 3
  23. 2023CNC-Net: Self-Supervised Learning for CNC Machining Operationscited by 3
  24. 2024MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Imagescited by 3
  25. 2026Mamba-CAD: State Space Model For 3D Computer-Aided Design Generative Modelingcited by 3
  26. 2024One Noise to Rule Them All: Learning a Unified Model of Spatially-Varying Noise Patternscited by 2
  27. 2025CADKnitter: Compositional CAD Generation from Text and Geometry Guidancecited by 2
  28. 2023P2CADNet: An End-to-End Reconstruction Network for Parametric 3D CAD Model from Point Cloudscited by 1
  29. 2024PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstructioncited by 1
  30. 2024A Unified Differentiable Boolean Operator with Fuzzy Logiccited by 1
  31. 2024Differentiable Convex Polyhedra Optimization from Multi-view Imagescited by 1
  32. 2022Taylor3DNet: Fast 3D Shape Inference With Landmark Points Based Taylor Seriescited by 0
  33. 2024Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogycited by 0
  34. 2026Unified Primitive Proxies for Structured Shape Completioncited by 0
  35. 2026AutoRegressive Generation with B-rep Holistic Token Sequence Representationcited by 0
  36. 2026Flatten The Complex: Joint B-Rep Generation via Compositional k-Cell Particlescited by 0
  37. 2026BrepGaussian: CAD reconstruction from Multi-View Images with Gaussian Splattingcited by 0
  38. 2026DualPrim: Compact 3D Reconstruction with Positive and Negative Primitivescited by 0

50 most cited of 51 All 51 (JSON)