mlsanityData to 14 Oct 2026

Point Cloud Instance Segmentation using Probabilistic Embeddings

arXiv 1912.00145 ↗First posted 30 Nov 2019cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

In this paper we propose a new framework for point cloud instance segmentation. Our framework has two steps: an embedding step and a clustering step. In the embedding step, our main contribution is to propose a probabilistic embedding space for point cloud embedding. Specifically, each point is represented as a tri-variate normal distribution. In the clustering step, we propose a novel loss function, which benefits both the semantic segmentation and the clustering. Our experimental results show important improvements to the SOTA, i.e., 3.1% increased average per-category mAP on the PartNet dataset.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 13; 2023: 13; 2024: 9; 2025: 10; 2026: 1.

52 papers.

Sort:

By area:

  1. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 200
  2. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 118
  3. 2022Superpoint Transformer for 3D Scene Instance Segmentationcited by 116
  4. 2021Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networkscited by 99
  5. 20214DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understandingcited by 54
  6. 2023ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolutioncited by 53
  7. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 46
  8. 2023PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimationcited by 37
  9. 20223D Instances as 1D Kernelscited by 36
  10. 2022MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentationcited by 30
  11. 2024Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentationcited by 30
  12. 2022Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarizationcited by 26
38 more
  1. 2023Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representationcited by 24
  2. 2021ICM-3D: Instantiated Category Modeling for 3D Instance Segmentationcited by 18
  3. 2023EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervisioncited by 18
  4. 2023ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentationcited by 18
  5. 2024PartSTAD: 2D-to-3D Part Segmentation Task Adaptationcited by 18
  6. 2025PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Datacited by 16
  7. 2021Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Miningcited by 15
  8. 2022Scalable SoftGroup for 3D Instance Segmentation on Point Cloudscited by 15
  9. 20243D Part Segmentation via Geometric Aggregation of 2D Visual Featurescited by 15
  10. 20223D-QueryIS: A Query-based Framework for 3D Instance Segmentationcited by 14
  11. 2024SUMix: Mixup with Semantic and Uncertain Informationcited by 12
  12. 2024Part2Object: Hierarchical Unsupervised 3D Instance Segmentationcited by 12
  13. 2025Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentationcited by 11
  14. 2021HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensorcited by 9
  15. 2023A Review of Panoptic Segmentation for Mobile Mapping Point Cloudscited by 8
  16. 2023End-to-End Supervised Multilabel Contrastive Learningcited by 8
  17. 2023Introspective Deep Metric Learningcited by 7
  18. 20233D Indoor Instance Segmentation in an Open-Worldcited by 7
  19. 2025U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequencescited by 7
  20. 2022ONeRF: Unsupervised 3D Object Segmentation from Multiple Viewscited by 6
  21. 2025All in One: Visual-Description-Guided Unified Point Cloud Segmentationcited by 4
  22. 2025SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Featurescited by 4
  23. 2025OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstructioncited by 4
  24. 2021Dynamic Convolution for 3D Point Cloud Instance Segmentationcited by 3
  25. 2022Scan2Part: Fine-grained and Hierarchical Part-level Understanding of Real-World 3D Scanscited by 3
  26. 2025Enhancing Partially Relevant Video Retrieval with Robust Alignment Learningcited by 3
  27. 2026SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Imagescited by 3
  28. 2022Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentationcited by 2
  29. 2022Seg&Struct: The Interplay Between Part Segmentation and Structure Inference for 3D Shape Parsingcited by 2
  30. 2024Improved Block Merging for 3D Point Cloud Instance Segmentationcited by 2
  31. 2024ProtoSeg: A Prototype-Based Point Cloud Instance Segmentation Methodcited by 2
  32. 2023Analogy-Forming Transformers for Few-Shot 3D Parsingcited by 1
  33. 2024Joint prototype and coefficient prediction for 3D instance segmentationcited by 1
  34. 2025CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentationcited by 1
  35. 2025Hierarchical Image-Guided 3D Point Cloud Segmentation in Industrial Scenes via Multi-View Bayesian Fusioncited by 1
  36. 2022Introspective Deep Metric Learning for Image Retrievalcited by 0
  37. 2023OSIS: Efficient One-stage Network for 3D Instance Segmentationcited by 0
  38. 2023PSGformer: Enhancing 3D Point Cloud Instance Segmentation via Precise Semantic Guidancecited by 0

50 most cited of 52 All 52 (JSON)