mlsanityData to 7 Oct 2026

JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints

arXiv 2111.12772 ↗First posted 24 Nov 2021cs.LG cs.CV cs.GRcited by 77

Not on the map. Why?

Abstract (arXiv)

Physical products are often complex assemblies combining a multitude of 3D parts modeled in computer-aided design (CAD) software. CAD designers build up these assemblies by aligning individual parts to one another using constraints called joints. In this paper we introduce JoinABLe, a learning-based method that assembles parts together to form joints. JoinABLe uses the weak supervision available in standard parametric CAD files without the help of object class labels or human guidance. Our results show that by making network predictions over a graph representation of solid models we can outperform multiple baseline methods with an accuracy (79.53%) that approaches human performance (80%). Finally, to support future research we release the Fusion 360 Gallery assembly dataset, containing assemblies with rich information on joints, contact surfaces, holes, and the underlying assembly graph structure.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). Builds on 29 of its 73 references that are in the map. First posted on arXiv 24 Nov 2021.

Builds on

29 of 73 references.

References · 29

  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2021How Attentive are Graph Attention Networks?cited by 818
  4. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  5. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  6. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  7. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266
  8. 2018Learning from positive and unlabeled data: a surveycited by 218
  9. 2019Category-Level Articulated Object Pose Estimationcited by 158
  10. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 118
  11. 2019Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapescited by 117
  12. 2019SDM-NET: Deep Generative Network for Structured Deformable Meshcited by 113
17 more
  1. 2021BRepNet: A topological message passing system for solid modelscited by 92
  2. 2019IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Taskscited by 68
  3. 2020Generative 3D Part Assembly via Dynamic Graph Learningcited by 65
  4. 2020Learning 3D Part Assembly from a Single Imagecited by 51
  5. 2021Inferring CAD Modeling Sequences Using Zone Graphscited by 50
  6. 2020Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequencescited by 36
  7. 2019Learning Part Generation and Assembly for Structure-aware Shape Synthesiscited by 35
  8. 2021RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assemblycited by 35
  9. 2020COALESCE: Component Assembly by Learning to Synthesize Connectionscited by 30
  10. 2020RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloudcited by 26
  11. 2020Learning Generative Models of Shape Handlescited by 25
  12. 2020Integrating Deep Learning into CAD/CAE System: Generative Design and Evaluation of 3D Conceptual Wheelcited by 25
  13. 2018Learning Robotic Assembly from CADcited by 21
  14. 2020ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesiscited by 19
  15. 2017ComplementMe: Weakly-Supervised Component Suggestions for 3D Modelingcited by 13
  16. 2021AutoMate: A Dataset and Learning Approach for Automatic Mating of CAD Assembliescited by 13
  17. 2020Compositionally Generalizable 3D Structure Predictioncited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 13; 2024: 13; 2025: 14; 2026: 27.

77 papers.

Sort:

By area:

  1. 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 101
  2. 2022SolidGen: An Autoregressive Model for Direct B-rep Synthesiscited by 78
  3. 2024SINGAPO: Single Image Controlled Generation of Articulated Parts in Objectscited by 66
  4. 2024ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidancecited by 59
  5. 2022Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priorscited by 42
  6. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
  7. 2022Breaking Bad: A Dataset for Geometric Fracture and Reassemblycited by 38
  8. 2024GenCAD: Image-Conditioned Computer-Aided Design Generation with Transformer-Based Contrastive Representation and Diffusion Priorscited by 36
  9. 2023Point2CAD: Reverse Engineering CAD Models from 3D Point Cloudscited by 33
  10. 2024DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassemblycited by 31
  11. 2025HoLa: B-Rep Generation using a Holistic Latent Representationcited by 29
  12. 2023Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assemblycited by 27
38 more
  1. 2023Jigsaw: Learning to Assemble Multiple Fractured Objectscited by 26
  2. 2022Self-Supervised Representation Learning for CADcited by 22
  3. 2023IKEA-Manual: Seeing Shape Assembly Step by Stepcited by 22
  4. 2023Category-Level Multi-Part Multi-Joint 3D Shape Assemblycited by 22
  5. 2025Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeekcited by 22
  6. 2025DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometrycited by 20
  7. 2022ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generationcited by 17
  8. 2023ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibilitycited by 17
  9. 2024Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solvingcited by 17
  10. 2022Translating a Visual LEGO Manual to a Machine-Executable Plancited by 15
  11. 2024Geometric Deep Learning for Computer-Aided Design: A Surveycited by 14
  12. 2025Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulationcited by 12
  13. 2025BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patchcited by 12
  14. 2024A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Partscited by 8
  15. 2024NeuroNURBS: Learning Efficient Surface Representations for 3D Solidscited by 8
  16. 2026ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generationcited by 7
  17. 2023Multi-level Reasoning for Robotic Assembly: From Sequence Inference to Contact Selectioncited by 5
  18. 2022Implicit Conversion of Manifold B-Rep Solids by Neural Halfspace Representationcited by 4
  19. 2022Budget-Aware Sequential Brick Assembly with Efficient Constraint Satisfactioncited by 4
  20. 2024Jigsaw++: Imagining Complete Shape Priors for Object Reassemblycited by 4
  21. 2025Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challengescited by 4
  22. 2026Embodied CAD: Solver-Grounded LLM Agents for Parametric B-Rep Assembly Modelingcited by 4
  23. 2022Material Prediction for Design Automation Using Graph Representation Learningcited by 3
  24. 2023A Survey of Methods for Converting Unstructured Data to CSG Modelscited by 3
  25. 2025BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assemblycited by 3
  26. 2026Masked BRep Autoencoder via Hierarchical Graph Transformercited by 3
  27. 2026neuralCAD-Edit: An Expert Benchmark for Multimodal-Instructed 3D CAD Model Editingcited by 3
  28. 2026CADEngBench: It Looks Like CAD, but Does It Work? Evaluating Parametric Design, Assembly Reasoning, and Physics Simulationcited by 3
  29. 2022Mates2Motion: Learning How Mechanical CAD Assemblies Workcited by 2
  30. 2023Generalizable Pose Estimation Using Implicit Scene Representationscited by 2
  31. 2023Representation Learning for Sequential Volumetric Design Taskscited by 2
  32. 2024Enabling Generative Design Tools with LLM Agents for Mechanical Computation Devices: A Case Studycited by 2
  33. 2025Better STEP, a format and dataset for boundary representationcited by 2
  34. 2025Target-Guided Bayesian Flow Networks for Quantitatively Constrained CAD Generationcited by 2
  35. 2025CADKnitter: Compositional CAD Generation from Text and Geometry Guidancecited by 2
  36. 2026COSMO-Agent: Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestrationcited by 2
  37. 2026Self-Improving CAD Generation Agents with Finite Element Analysis as Feedbackcited by 2
  38. 2023What's in a Name? Evaluating Assembly-Part Semantic Knowledge in Language Models through User-Provided Names in CAD Filescited by 1

50 most cited of 77 All 77 (JSON)