mlsanityData to 14 Oct 2026

Constraint-Aware Feature Learning for Parametric Point Cloud

arXiv 2411.07747 ↗First posted 12 Nov 2024cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Parametric point clouds are sampled from CAD shapes and are becoming increasingly common in industrial manufacturing. Most CAD-specific deep learning methods focus on geometric features, while overlooking constraints inherent in CAD shapes. This limits their ability to discern CAD shapes with similar appearances but different constraints. To tackle this challenge, we first analyze the constraint importance via simple validation experiments. Then, we introduce a deep learning-friendly constraints representation with three components, and design a constraint-aware feature learning network (CstNet), which includes two stages. Stage 1 extracts constraint representation from BRep data or point cloud based on local features. It enables better generalization ability to unseen dataset after pre-training. Stage 2 employs attention layers to adaptively adjust the weights of three constraints' components. It facilitates the effective utilization of constraints. In addition, we built the first multi-modal parametric-purpose dataset, i.e. Param20K, comprising about 20K CAD instances of 75 classes. On this dataset, CstNet achieved 3.49% (classification) and 26.17% (rotation robustness) accuracy improvements over the state-of-the-art. To the best of our knowledge, CstNet is the first constraint-aware deep learning method tailored for parametric point cloud analysis.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 42 of its 84 references that are in the map. First posted on arXiv 12 Nov 2024.

Builds on

42 of 84 references.

References · 42

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  4. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  5. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  6. 2020PCT: Point cloud transformercited by 732
  7. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  8. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  9. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  10. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  11. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  12. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
30 more
  1. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 341
  2. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 271
  3. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  4. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  5. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  6. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 167
  7. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  8. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  9. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  10. 2022SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebookscited by 125
  11. 2020H3DNet: 3D Object Detection Using Hybrid Geometric Primitivescited by 123
  12. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  13. 2021BRepNet: A topological message passing system for solid modelscited by 95
  14. 2018Supervised Fitting of Geometric Primitives to 3D Point Cloudscited by 91
  15. 2018Recurrent Slice Networks for 3D Segmentation of Point Cloudscited by 82
  16. 2021Computer-Aided Design as Languagecited by 82
  17. 2021JoinABLe: Learning Bottom-up Assembly of Parametric CAD Jointscited by 78
  18. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  19. 2021SketchGen: Generating Constrained CAD Sketchescited by 68
  20. 2021Vitruvion: A Generative Model of Parametric CAD Sketchescited by 66
  21. 20163D Shape Segmentation with Projective Convolutional Networkscited by 63
  22. 2021Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinderscited by 60
  23. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  24. 2021HPNet: Deep Primitive Segmentation Using Hybrid Representationscited by 36
  25. 2022CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representationscited by 31
  26. 2024Freehand Sketch Generation from Mechanical Componentscited by 8
  27. 2018"FabSearch" : A 3D CAD Model Based Search Engine for Sourcing Manufacturing Servicescited by 7
  28. 2021A Convolutional Neural Network Approach to the Classification of Engineering Modelscited by 5
  29. 2024SD-Net: Symmetric-Aware Keypoint Prediction and Domain Adaptation for 6D Pose Estimation In Bin-picking Scenarioscited by 3
  30. 2024Training-Free Point Cloud Recognition Based on Geometric and Semantic Information Fusioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026KDH-CAD: Knowledge-data hybrid CAD learning under data scarcitycited by 0