mlsanityData to 7 Oct 2026

Novel Class Discovery for 3D Point Cloud Semantic Segmentation

arXiv 2303.11610 ↗First posted 21 Mar 2023cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Novel class discovery (NCD) for semantic segmentation is the task of learning a model that can segment unlabelled (novel) classes using only the supervision from labelled (base) classes. This problem has recently been pioneered for 2D image data, but no work exists for 3D point cloud data. In fact, the assumptions made for 2D are loosely applicable to 3D in this case. This paper is presented to advance the state of the art on point cloud data analysis in four directions. Firstly, we address the new problem of NCD for point cloud semantic segmentation. Secondly, we show that the transposition of the only existing NCD method for 2D semantic segmentation to 3D data is suboptimal. Thirdly, we present a new method for NCD based on online clustering that exploits uncertainty quantification to produce prototypes for pseudo-labelling the points of the novel classes. Lastly, we introduce a new evaluation protocol to assess the performance of NCD for point cloud semantic segmentation. We thoroughly evaluate our method on SemanticKITTI and SemanticPOSS datasets, showing that it can significantly outperform the baseline. Project page at this link: https://github.com/LuigiRiz/NOPS.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 35 of its 46 references that are in the map. First posted on arXiv 21 Mar 2023.

Builds on

35 of 46 references.

References · 35

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  7. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  8. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  10. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  11. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  12. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
23 more
  1. 2019Self-labelling via simultaneous clustering and representation learningcited by 525
  2. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 454
  3. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  4. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  5. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  6. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  7. 2017Submanifold Sparse Convolutional Networkscited by 223
  8. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 223
  9. 2022Generalized Category Discoverycited by 209
  10. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  11. 2021A Unified Objective for Novel Class Discoverycited by 161
  12. 2020SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instancescited by 123
  13. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 119
  14. 2020OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open Worldcited by 93
  15. 20203D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentationcited by 58
  16. 2021Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Datacited by 55
  17. 2022CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentationcited by 54
  18. 2022Class-incremental Novel Class Discoverycited by 42
  19. 2022Novel Class Discovery without Forgettingcited by 39
  20. 2021Novel Class Discovery in Semantic Segmentationcited by 31
  21. 2022Open-world Semantic Segmentation for LIDAR Point Cloudscited by 29
  22. 2022Overlap-guided Gaussian Mixture Models for Point Cloud Registrationcited by 10
  23. 2022Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understandingcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 4; 2025: 8; 2026: 1.

21 papers.

Sort:

By area:

  1. 2023Towards Label-free Scene Understanding by Vision Foundation Modelscited by 54
  2. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  3. 2023A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Applicationcited by 21
  4. 2023Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discoverycited by 11
  5. 2024Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentationcited by 9
  6. 2024AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarioscited by 9
  7. 2024Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perceptioncited by 8
  8. 2025Category Discovery: An Open-World Perspectivecited by 5
  9. 2023Generalized Category Discovery in Semantic Segmentationcited by 4
  10. 2023Novel class discovery meets foundation models for 3D semantic segmentationcited by 4
  11. 2024PanoSLAM: Panoptic 3D Scene Reconstruction via Gaussian SLAMcited by 3
  12. 2025Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoningcited by 2
9 more
  1. 2023OpenPatch: a 3D patchwork for Out-Of-Distribution detectioncited by 1
  2. 2025A Novel Decomposed Feature-Oriented Framework for Open-Set Semantic Segmentation on LiDAR Datacited by 1
  3. 2023Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class Discoverycited by 0
  4. 2025Improving Open-Set Semantic Segmentation in 3D Point Clouds by Conditional Channel Capacity Maximization: Preliminary Resultscited by 0
  5. 2025Deeply Dual Supervised learning for melanoma recognitioncited by 0
  6. 2025Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsamplingcited by 0
  7. 2025DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentationcited by 0
  8. 2025VesselRW: Weakly Supervised Subcutaneous Vessel Segmentation via Learned Random Walk Propagationcited by 0
  9. 2026Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentationcited by 0