mlsanityData to 7 Oct 2026

PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentation

arXiv 2404.00979 ↗First posted 1 Apr 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Existing point cloud semantic segmentation networks cannot identify unknown classes and update their knowledge, due to a closed-set and static perspective of the real world, which would induce the intelligent agent to make bad decisions. To address this problem, we propose a Probability-Driven Framework (PDF) for open world semantic segmentation that includes (i) a lightweight U-decoder branch to identify unknown classes by estimating the uncertainties, (ii) a flexible pseudo-labeling scheme to supply geometry features along with probability distribution features of unknown classes by generating pseudo labels, and (iii) an incremental knowledge distillation strategy to incorporate novel classes into the existing knowledge base gradually. Our framework enables the model to behave like human beings, which could recognize unknown objects and incrementally learn them with the corresponding knowledge. Experimental results on the S3DIS and ScanNetv2 datasets demonstrate that the proposed PDF outperforms other methods by a large margin in both important tasks of open world semantic segmentation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 42 of its 50 references that are in the map. First posted on arXiv 1 Apr 2024.

Builds on

42 of 50 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  8. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  9. 2016Learning without Forgettingcited by 2,465
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  12. 2020Point Transformercited by 1,462
30 more
  1. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  2. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  3. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  4. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  5. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  6. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  7. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  8. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  9. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  10. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  11. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  12. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  13. 2014Towards Open World Recognitioncited by 226
  14. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  15. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  16. 2019Detecting the Unexpected via Image Resynthesiscited by 137
  17. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  18. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 124
  19. 2021Learning Placeholders for Open-Set Recognitioncited by 121
  20. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  21. 2021Fast Point Transformercited by 103
  22. 2020Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentationcited by 96
  23. 2023RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Drivingcited by 76
  24. 2018VV-Net: Voxel VAE Net with Group Convolutions for Point Cloud Segmentationcited by 64
  25. 2021Deep Metric Learning for Open World Semantic Segmentationcited by 51
  26. 2019Octree guided CNN with Spherical Kernels for 3D Point Cloudscited by 50
  27. 2021Energy-Based Open-World Uncertainty Modeling for Confidence Calibrationcited by 46
  28. 2018Fully-Convolutional Point Networks for Large-Scale Point Cloudscited by 44
  29. 2021Exemplar-Based Open-Set Panoptic Segmentation Networkcited by 37
  30. 2022Open-world Semantic Segmentation for LIDAR Point Cloudscited by 29

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Cloudscited by 8
  2. 2025A Novel Decomposed Feature-Oriented Framework for Open-Set Semantic Segmentation on LiDAR Datacited by 1
  3. 2025Improving Open-Set Semantic Segmentation in 3D Point Clouds by Conditional Channel Capacity Maximization: Preliminary Resultscited by 0
  4. 2025Open-world Point Cloud Semantic Segmentation: A Human-in-the-loop Frameworkcited by 0