mlsanityData to 7 Oct 2026

Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions

arXiv 2003.13834 ↗First posted 30 Mar 2020cs.CV cs.GR cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

The problems of shape classification and part segmentation from 3D point clouds have garnered increasing attention in the last few years. Both of these problems, however, suffer from relatively small training sets, creating the need for statistically efficient methods to learn 3D shape representations. In this paper, we investigate the use of Approximate Convex Decompositions (ACD) as a self-supervisory signal for label-efficient learning of point cloud representations. We show that using ACD to approximate ground truth segmentation provides excellent self-supervision for learning 3D point cloud representations that are highly effective on downstream tasks. We report improvements over the state-of-the-art for unsupervised representation learning on the ModelNet40 shape classification dataset and significant gains in few-shot part segmentation on the ShapeNetPart dataset.Code available at https://github.com/matheusgadelha/PointCloudLearningACD

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 10; 2023: 7; 2024: 3; 2025: 1; 2026: 1.

27 papers.

Sort:

By area:

  1. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 117
  2. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  3. 2021Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learningcited by 52
  4. 2023PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimationcited by 37
  5. 2023PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillationcited by 27
  6. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  7. 2023ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentationcited by 18
  8. 2022Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learningcited by 13
  9. 2022MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentationcited by 10
  10. 20243x2: 3D Object Part Segmentation by 2D Semantic Correspondencescited by 10
  11. 2024PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Modelcited by 9
  12. 2022Semi-supervised 3D shape segmentation with multilevel consistency and part substitutioncited by 8
15 more
  1. 2021Representing Shape Collections with Alignment-Aware Linear Modelscited by 7
  2. 2021PriFit: Learning to Fit Primitives Improves Few Shot Point Cloud Segmentationcited by 6
  3. 2021Point Discriminative Learning for Data-efficient 3D Point Cloud Analysiscited by 5
  4. 2022Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentationcited by 5
  5. 2021The Neurally-Guided Shape Parser: Grammar-based Labeling of 3D Shape Regions with Approximate Inferencecited by 4
  6. 2023Novel class discovery meets foundation models for 3D semantic segmentationcited by 4
  7. 2022Self-Supervised Feature Learning from Partial Point Clouds via Pose Disentanglementcited by 3
  8. 2022Open-Set Semi-Supervised Learning for 3D Point Cloud Understandingcited by 3
  9. 2022Semi-supervised segmentation of tooth from 3D Scanned Dental Archescited by 3
  10. 2022SHRED: 3D Shape Region Decomposition with Learned Local Operationscited by 1
  11. 2023Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignmentcited by 1
  12. 2024Semantic-Free Procedural 3D Shapes Are Surprisingly Good Teacherscited by 1
  13. 2026Learning Convex Decomposition via Feature Fieldscited by 1
  14. 2023Concavity-Induced Distance for Unoriented Point Cloud Decompositioncited by 0
  15. 2025Random Walks in Self-supervised Learning for Triangular Meshescited by 0