mlsanityData to 14 Oct 2026

Category-Level Multi-Part Multi-Joint 3D Shape Assembly

arXiv 2303.06163 ↗First posted 10 Mar 2023cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Shape assembly composes complex shapes geometries by arranging simple part geometries and has wide applications in autonomous robotic assembly and CAD modeling. Existing works focus on geometry reasoning and neglect the actual physical assembly process of matching and fitting joints, which are the contact surfaces connecting different parts. In this paper, we consider contacting joints for the task of multi-part assembly. A successful joint-optimized assembly needs to satisfy the bilateral objectives of shape structure and joint alignment. We propose a hierarchical graph learning approach composed of two levels of graph representation learning. The part graph takes part geometries as input to build the desired shape structure. The joint-level graph uses part joints information and focuses on matching and aligning joints. The two kinds of information are combined to achieve the bilateral objectives. Extensive experiments demonstrate that our method outperforms previous methods, achieving better shape structure and higher joint alignment accuracy.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 28 of its 62 references that are in the map. First posted on arXiv 10 Mar 2023.

Builds on

28 of 62 references.

References · 28

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  3. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  4. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  5. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 341
  6. 2018Graph R-CNN for Scene Graph Generationcited by 298
  7. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 271
  8. 2017Scene Graph Generation from Objects, Phrases and Region Captionscited by 154
  9. 2018Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Taskscited by 154
  10. 2019Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapescited by 119
  11. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 119
  12. 2019SDM-NET: Deep Generative Network for Structured Deformable Meshcited by 113
16 more
  1. 2018Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Modelscited by 106
  2. 2021JoinABLe: Learning Bottom-up Assembly of Parametric CAD Jointscited by 78
  3. 2019IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Taskscited by 69
  4. 2020Generative 3D Part Assembly via Dynamic Graph Learningcited by 67
  5. 2019SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentationcited by 55
  6. 2020Learning 3D Part Assembly from a Single Imagecited by 52
  7. 2019Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassemblycited by 51
  8. 2021Inferring CAD Modeling Sequences Using Zone Graphscited by 50
  9. 2022Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priorscited by 43
  10. 2019Learning Part Generation and Assembly for Structure-aware Shape Synthesiscited by 36
  11. 2021RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assemblycited by 36
  12. 2019Scene Graph Prediction with Limited Labelscited by 32
  13. 2020COALESCE: Component Assembly by Learning to Synthesize Connectionscited by 30
  14. 2020Learning Generative Models of Shape Handlescited by 25
  15. 2018Learning Robotic Assembly from CADcited by 21
  16. 2020Compositionally Generalizable 3D Structure Predictioncited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 8; 2025: 7; 2026: 6.

22 papers.

Sort:

By area:

  1. 2024SINGAPO: Single Image Controlled Generation of Articulated Parts in Objectscited by 69
  2. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 40
  3. 2025PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understandingcited by 26
  4. 2023NAP: Neural 3D Articulation Priorcited by 25
  5. 2024PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verifycited by 15
  6. 2025Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Modelscited by 14
  7. 2025Rectified Point Flow: Generic Point Cloud Pose Estimationcited by 14
  8. 2024SPAFormer: Sequential 3D Part Assembly with Transformerscited by 12
  9. 2024A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Partscited by 9
  10. 2024Manual-PA: Learning 3D Part Assembly from Instruction Diagramscited by 7
  11. 2024Jigsaw++: Imagining Complete Shape Priors for Object Reassemblycited by 6
  12. 2025Manual2Skill++: Connector-Aware General Robotic Assembly from Instruction Manuals via Vision-Language Modelscited by 5
10 more
  1. 2026TORA: Topological Representation Alignment for 3D Shape Assemblycited by 4
  2. 2024Geometric Point Attention Transformer for 3D Shape Reassemblycited by 3
  3. 2025Combinative Matching for Geometric Shape Assemblycited by 3
  4. 2026A3D: Adaptive Affordance Assembly with Dual-Arm Manipulationcited by 3
  5. 2025Text to Robotic Assembly of Multi Component Objects using 3D Generative AI and Vision Language Modelscited by 2
  6. 2026AssemblyBench: Physics-Aware Assembly of Complex Industrial Objectscited by 2
  7. 2025Prompt2Craft: Generating Functional Craft Assemblies with LLMscited by 0
  8. 2026MixRI: Mixing Features of Reference Images for Novel Object Pose Estimationcited by 0
  9. 2026PART: Learning 3D Part Assembly and Retrieval with Transformerscited by 0
  10. 2026AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agentscited by 0