mlsanityData to 7 Oct 2026

Unsupervised Point Cloud Completion through Unbalanced Optimal Transport

arXiv 2410.02671 ↗First posted 3 Oct 2024cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Unpaired point cloud completion is crucial for real-world applications, where ground-truth data for complete point clouds are often unavailable. By learning a completion map from unpaired incomplete and complete point cloud data, this task avoids the reliance on paired datasets. In this paper, we propose the textitUnbalanced Optimal Transport Map for Unpaired Point Cloud Completion (UOT-UPC) model, which formulates the unpaired completion task as the (Unbalanced) Optimal Transport (OT) problem. Our method employs a Neural OT model learning the UOT map using neural networks. Our model is the first attempt to leverage UOT for unpaired point cloud completion, achieving competitive or superior performance on both single-category and multi-category benchmarks. In particular, our approach is especially robust under the class imbalance problem, which is frequently encountered in real-world unpaired point cloud completion scenarios. The code is available at https://github.com/LEETK99/UOT-UPC.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 43 references that are in the map. First posted on arXiv 3 Oct 2024.

Builds on

27 of 43 references.

References · 27

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  4. 2018Computational Optimal Transportcited by 765
  5. 2018Which Training Methods for GANs do actually Converge?cited by 672
  6. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  7. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  8. 2018PCN: Point Completion Networkcited by 382
  9. 2021GAN Inversion: A Surveycited by 366
  10. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  11. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  12. 2015Optimal Entropy-Transport problems and a new Hellinger-Kantorovich distance between positive measurescited by 138
15 more
  1. 2017Stabilizing Training of Generative Adversarial Networks through Regularizationcited by 118
  2. 2021Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmarkcited by 95
  3. 2020Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptationcited by 86
  4. 2021Generative Modeling with Optimal Transport Mapscited by 80
  5. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
  6. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  7. 2020Multimodal Shape Completion via Conditional Generative Adversarial Networkscited by 61
  8. 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
  9. 2022Unbalanced Optimal Transport, from Theory to Numericscited by 45
  10. 2021Neural Monge Map estimation and its applicationscited by 40
  11. 2023Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transportcited by 39
  12. 2023Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translationcited by 32
  13. 2021ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completioncited by 28
  14. 2022Learning Local Displacements for Point Cloud Completioncited by 16
  15. 2023Analyzing and Improving Optimal-Transport-based Adversarial Networkscited by 8

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plancited by 6