mlsanityData to 14 Oct 2026

3D Geometric Shape Assembly via Efficient Point Cloud Matching

arXiv 2407.10542 ↗First posted 15 Jul 2024cs.CV cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both coarse- and fine-levels. To this end, we introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts while incurring low costs in memory and computation. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad and demonstrate its superior performance and efficiency compared to state-of-the-art methods. Project page: https://nahyuklee.github.io/pmtr.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 37 of its 50 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

37 of 50 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2020Big Bird: Transformers for Longer Sequencescited by 1,684
  4. 2018Group Normalizationcited by 1,524
  5. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  7. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  8. 2020Transporter Networks: Rearranging the Visual World for Robotic Manipulationcited by 344
  9. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 306
  10. 2019On the Relationship between Self-Attention and Convolutional Layerscited by 300
  11. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 290
  12. 2020Deep Global Registrationcited by 229
25 more
  1. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 202
  2. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  3. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  4. 2018Neighbourhood Consensus Networkscited by 174
  5. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 152
  6. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 119
  7. 2020Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutionscited by 93
  8. 2021CATs: Cost Aggregation Transformers for Visual Correspondencecited by 77
  9. 2020Generative 3D Part Assembly via Dynamic Graph Learningcited by 67
  10. 2022ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matchingcited by 62
  11. 2020Learning 3D Part Assembly from a Single Imagecited by 52
  12. 2019Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassemblycited by 51
  13. 2020Shonan Rotation Averaging: Global Optimality by Surfing SO(p)ncited by 46
  14. 2021Convolutional Hough Matching Networkscited by 43
  15. 2022Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priorscited by 43
  16. 2022Breaking Bad: A Dataset for Geometric Fracture and Reassemblycited by 41
  17. 2019Learning Part Generation and Assembly for Structure-aware Shape Synthesiscited by 36
  18. 2021RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assemblycited by 36
  19. 2022TransforMatcher: Match-to-Match Attention for Semantic Correspondencecited by 29
  20. 2023Jigsaw: Learning to Assemble Multiple Fractured Objectscited by 29
  21. 2023Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assemblycited by 28
  22. 2022Peripheral Vision Transformercited by 27
  23. 2018Stable bin packing of non-convex 3D objects with a robot manipulatorcited by 21
  24. 2019Unsupervised Primitive Discovery for Improved 3D Generative Modelingcited by 8
  25. 2023Graph Matching Optimization Network for Point Cloud Registrationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 3.

9 papers.

  1. 2025GARF: Learning Generalizable 3D Reassembly for Real-World Fracturescited by 13
  2. 2024A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Partscited by 9
  3. 2025BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assemblycited by 5
  4. 2026TORA: Topological Representation Alignment for 3D Shape Assemblycited by 4
  5. 2024Geometric Point Attention Transformer for 3D Shape Reassemblycited by 3
  6. 2025Combinative Matching for Geometric Shape Assemblycited by 3
  7. 2025E-M3RF: An Equivariant Multimodal 3D Re-assembly Frameworkcited by 1
  8. 2026CRAG: Can 3D Generative Models Help 3D Assembly?cited by 1
  9. 2026LLM2R: From Large Language Models to 3D Reassemblerscited by 0