mlsanityData to 7 Oct 2026

SPA-VAE: Similar-Parts-Assignment for Unsupervised 3D Point Cloud Generation

arXiv 2203.07825 ↗First posted 15 Mar 2022cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

This paper addresses the problem of unsupervised parts-aware point cloud generation with learned parts-based self-similarity. Our SPA-VAE infers a set of latent canonical candidate shapes for any given object, along with a set of rigid body transformations for each such candidate shape to one or more locations within the assembled object. In this way, noisy samples on the surface of, say, each leg of a table, are effectively combined to estimate a single leg prototype. When parts-based self-similarity exists in the raw data, sharing data among parts in this way confers numerous advantages: modeling accuracy, appropriately self-similar generative outputs, precise in-filling of occlusions, and model parsimony. SPA-VAE is trained end-to-end using a variational Bayesian approach which uses the Gumbel-softmax trick for the shared part assignments, along with various novel losses to provide appropriate inductive biases. Quantitative and qualitative analyses on ShapeNet demonstrate the advantage of SPA-VAE.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 58 of its 88 references that are in the map. First posted on arXiv 15 Mar 2022.

Builds on

58 of 88 references.

References · 58

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  7. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  9. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  10. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  11. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  12. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
38 more
  1. 2018PCN: Point Completion Networkcited by 382
  2. 2018Understanding disentangling in β-VAEcited by 332
  3. 2020Learning Gradient Fields for Shape Generationcited by 245
  4. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  5. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  6. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  7. 2019Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wildcited by 180
  8. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  9. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  10. 2019CvxNet: Learnable Convex Decompositioncited by 173
  11. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 162
  12. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  13. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  14. 2021Similarity Reasoning and Filtration for Image-Text Matchingcited by 121
  15. 2020Cascaded Refinement Network for Point Cloud Completioncited by 112
  16. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  17. 2020SoftFlow: Probabilistic Framework for Normalizing Flow on Manifoldscited by 97
  18. 2020PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Pathscited by 97
  19. 2021Region Similarity Representation Learningcited by 96
  20. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  21. 2020Discrete Point Flow Networks for Efficient Point Cloud Generationcited by 87
  22. 2020Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Imagecited by 72
  23. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
  24. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  25. 2020Multimodal Shape Completion via Conditional Generative Adversarial Networkscited by 61
  26. 2019StructureNet: Hierarchical Graph Networks for 3D Shape Generationcited by 59
  27. 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
  28. 2020Progressive Point Cloud Deconvolution Generation Networkcited by 46
  29. 2021Style-based Point Generator with Adversarial Rendering for Point Cloud Completioncited by 45
  30. 2021Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Cloudscited by 44
  31. 2020Weakly-supervised 3D Shape Completion in the Wildcited by 33
  32. 2021Voxel-based Network for Shape Completion by Leveraging Edge Generationcited by 32
  33. 2019Composite Shape Modeling via Latent Space Factorizationcited by 31
  34. 2021Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognitioncited by 31
  35. 2020Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetrycited by 24
  36. 2020Skeleton-bridged Point Completion: From Global Inference to Local Adjustmentcited by 23
  37. 2020Image-to-Image Retrieval by Learning Similarity between Scene Graphscited by 23
  38. 2021SP-GAN: Sphere-Guided 3D Shape Generation and Manipulationcited by 21

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 1.

2 papers.

  1. 2023FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generationcited by 9
  2. 2026Quartet of Diffusions: Structure-Aware Point Cloud Generation through Part and Symmetry Guidancecited by 1