mlsanityData to 7 Oct 2026

Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning

arXiv 1904.02113 ↗First posted 3 Apr 2019cs.CV cs.LGcited by 42

Not on the map. Why?

Abstract (arXiv)

We propose a new supervized learning framework for oversegmenting 3D point clouds into superpoints. We cast this problem as learning deep embeddings of the local geometry and radiometry of 3D points, such that the border of objects presents high contrasts. The embeddings are computed using a lightweight neural network operating on the points' local neighborhood. Finally, we formulate point cloud oversegmentation as a graph partition problem with respect to the learned embeddings. This new approach allows us to set a new state-of-the-art in point cloud oversegmentation by a significant margin, on a dense indoor dataset (S3DIS) and a sparse outdoor one (vKITTI). Our best solution requires over five times fewer superpoints to reach similar performance than previously published methods on S3DIS. Furthermore, we show that our framework can be used to improve superpoint-based semantic segmentation algorithms, setting a new state-of-the-art for this task as well.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 15; 2022: 10; 2023: 11; 2024: 2; 2025: 4.

42 papers.

Sort:

By area:

  1. 2021Spherical Message Passing for 3D Graph Networkscited by 166
  2. 2021InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referringcited by 140
  3. 2021Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networkscited by 98
  4. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 71
  5. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  6. 2023Efficient 3D Semantic Segmentation with Superpoint Transformercited by 56
  7. 20213D Siamese Voxel-to-BEV Tracker for Sparse Point Cloudscited by 54
  8. 2023ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolutioncited by 52
  9. 2022Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentationcited by 47
  10. 2021PVT: Point-Voxel Transformer for Point Cloud Learningcited by 42
  11. 2023Clustering based Point Cloud Representation Learning for 3D Analysiscited by 23
  12. 2023Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representationcited by 23
30 more
  1. 2021Voint Cloud: Multi-View Point Cloud Representation for 3D Understandingcited by 22
  2. 2021Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Cloudscited by 19
  3. 2022Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradientscited by 17
  4. 2022Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoningcited by 16
  5. 2023SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detectioncited by 11
  6. 2025Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphscited by 10
  7. 2021A Technical Survey and Evaluation of Traditional Point Cloud Clustering Methods for LiDAR Panoptic Segmentationcited by 9
  8. 2021A Divide-and-Merge Point Cloud Clustering Algorithm for LiDAR Panoptic Segmentationcited by 9
  9. 2022MVTN: Learning Multi-View Transformations for 3D Understandingcited by 7
  10. 2023Region-Enhanced Feature Learning for Scene Semantic Segmentationcited by 6
  11. 2022PSSNet: Planarity-sensible Semantic Segmentation of Large-scale Urban Meshescited by 5
  12. 2021Picasso: A CUDA-based Library for Deep Learning over 3D Meshescited by 4
  13. 2021Mesh Convolution with Continuous Filters for 3D Surface Parsingcited by 4
  14. 2022Upsampling Autoencoder for Self-Supervised Point Cloud Learningcited by 4
  15. 2021SPNet: Multi-Shell Kernel Convolution for Point Cloud Semantic Segmentationcited by 3
  16. 2023GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentationcited by 3
  17. 2021Generating Unrestricted 3D Adversarial Point Cloudscited by 2
  18. 2022Completing Partial Point Clouds with Outliers by Collaborative Completion and Segmentationcited by 2
  19. 2023Enhancing Surface Neural Implicits with Curvature-Guided Sampling and Uncertainty-Augmented Representationscited by 2
  20. 2024PointViG: A Lightweight GNN-based Model for Efficient Point Cloud Analysiscited by 2
  21. 2023GeoSpark: Sparking up Point Cloud Segmentation with Geometry Cluecited by 1
  22. 2023Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignmentcited by 1
  23. 2025SPPSFormer: High-quality Superpoint-based Transformer for Roof Plane Instance Segmentation from Point Cloudscited by 1
  24. 2025EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentationcited by 1
  25. 2021Potential Convolution: Embedding Point Clouds into Potential Fieldscited by 0
  26. 2022Global Hierarchical Attention for 3D Point Cloud Analysiscited by 0
  27. 2022Effective Utilisation of Multiple Open-Source Datasets to Improve Generalisation Performance of Point Cloud Segmentation Modelscited by 0
  28. 2023A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptorscited by 0
  29. 2024Efficiently Expanding Receptive Fields: Local Split Attention and Parallel Aggregation for Enhanced Large-scale Point Cloud Semantic Segmentationcited by 0
  30. 2025NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentationcited by 0