mlsanityData to 14 Oct 2026

PriFit: Learning to Fit Primitives Improves Few Shot Point Cloud Segmentation

arXiv 2112.13942 ↗First posted 27 Dec 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

We present PriFit, a semi-supervised approach for label-efficient learning of 3D point cloud segmentation networks. PriFit combines geometric primitive fitting with point-based representation learning. Its key idea is to learn point representations whose clustering reveals shape regions that can be approximated well by basic geometric primitives, such as cuboids and ellipsoids. The learned point representations can then be re-used in existing network architectures for 3D point cloud segmentation, and improves their performance in the few-shot setting. According to our experiments on the widely used ShapeNet and PartNet benchmarks, PriFit outperforms several state-of-the-art methods in this setting, suggesting that decomposability into primitives is a useful prior for learning representations predictive of semantic parts. We present a number of ablative experiments varying the choice of geometric primitives and downstream tasks to demonstrate the effectiveness of the method.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 33 of its 66 references that are in the map. First posted on arXiv 27 Dec 2021.

Builds on

33 of 66 references.

References · 33

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  6. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  7. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  8. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 504
  9. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 488
  10. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  11. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  12. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
21 more
  1. 2019CvxNet: Learnable Convex Decompositioncited by 174
  2. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 124
  3. 2015Gradient Estimation Using Stochastic Computation Graphscited by 121
  4. 20183D Point Capsule Networkscited by 106
  5. 2020ParSeNet: A Parametric Surface Fitting Network for 3D Point Cloudscited by 96
  6. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  7. 2018Supervised Fitting of Geometric Primitives to 3D Point Cloudscited by 91
  8. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  9. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  10. 2020Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Imagecited by 72
  11. 2017Recurrent Pixel Embedding for Instance Groupingcited by 58
  12. 2021Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Cloudscited by 44
  13. 2020Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categoriescited by 30
  14. 2020Label-Efficient Learning on Point Clouds using Approximate Convex Decompositionscited by 27
  15. 2020Learning Generative Models of Shape Handlescited by 25
  16. 2020Joint Supervised and Self-Supervised Learning for 3D Real-World Challengescited by 21
  17. 2020Neural Star Domain as Primitive Representationcited by 17
  18. 2019MortonNet: Self-Supervised Learning of Local Features in 3D Point Cloudscited by 9
  19. 2019Learning Point Embeddings from Shape Repositories for Few-Shot Segmentationcited by 5
  20. 2017Tags2Parts: Discovering Semantic Regions from Shape Tagscited by 4
  21. 2013Bayesian Inference in Model-Based Machine Visioncited by 1

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 1.

6 papers.

  1. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 118
  2. 2023Marching-Primitives: Shape Abstraction from Signed Distance Functioncited by 19
  3. 2023Iterative Superquadric Recomposition of 3D Objects from Multiple Viewscited by 13
  4. 2022MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentationcited by 10
  5. 2024SweepNet: Unsupervised Learning Shape Abstraction via Neural Sweeperscited by 5
  6. 2023Recognising geometric primitives in 3D point clouds of mechanical CAD objectscited by 4