mlsanityData to 13 Oct 2026

3DOS: Towards 3D Open Set Learning -- Benchmarking and Understanding Semantic Novelty Detection on Point Clouds

arXiv 2207.11554 ↗First posted 23 Jul 2022cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

In recent years there has been significant progress in the field of 3D learning on classification, detection and segmentation problems. The vast majority of the existing studies focus on canonical closed-set conditions, neglecting the intrinsic open nature of the real-world. This limits the abilities of robots and autonomous systems involved in safety-critical applications that require managing novel and unknown signals. In this context exploiting 3D data can be a valuable asset since it provides rich information about the geometry of perceived objects and scenes. With this paper we provide the first broad study on 3D Open Set learning. We introduce 3DOS: a novel testbed for semantic novelty detection that considers several settings with increasing difficulties in terms of semantic (category) shift, and covers both in-domain (synthetic-to-synthetic, real-to-real) and cross-domain (synthetic-to-real) scenarios. Moreover, we investigate the related 2D Open Set literature to understand if and how its recent improvements are effective on 3D data. Our extensive benchmark positions several algorithms in the same coherent picture, revealing their strengths and limitations. The results of our analysis may serve as a reliable foothold for future tailored 3D Open Set methods.

Key facts. Cited by 11 papers in the map (data through 13 Oct 2026). Builds on 50 of its 61 references that are in the map. First posted on arXiv 23 Jul 2022.

Builds on

50 of 61 references.

References · 50

  1. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,457
  2. 2017On Calibration of Modern Neural Networkscited by 4,902
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,389
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,889
  5. 2020Supervised Contrastive Learningcited by 2,811
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,371
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,222
  8. 2016Density estimation using Real NVPcited by 2,033
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,475
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,327
  11. 2020Energy-based Out-of-distribution Detectioncited by 1,297
  12. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 970
38 more
  1. 2018Deep Anomaly Detection with Outlier Exposurecited by 941
  2. 2021Generalized Out-of-Distribution Detection: A Surveycited by 799
  3. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  4. 2020PCT: Point cloud transformercited by 731
  5. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  6. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  7. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  8. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  9. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  10. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  11. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  12. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  13. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  14. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  15. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  16. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  17. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  18. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  19. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
  20. 2020ATOM: Robustifying Out-of-distribution Detection Using Outlier Miningcited by 116
  21. 2020Learning Open Set Network with Discriminative Reciprocal Pointscited by 115
  22. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  23. 2020Hybrid Models for Open Set Recognitioncited by 109
  24. 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
  25. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 80
  26. 2019Identifying Unknown Instances for Autonomous Drivingcited by 73
  27. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  28. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  29. 2020Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classificationcited by 57
  30. 2021Optimal Representations for Covariate Shiftcited by 51
  31. 2020Feature Space Singularity for Out-of-Distribution Detectioncited by 49
  32. 2021Open-set 3D Object Detectioncited by 29
  33. 2019P-ODN: Prototype based Open Deep Network for Open Set Recognitioncited by 28
  34. 2019Novelty Detection Via Blurringcited by 24
  35. 2020Joint Supervised and Self-Supervised Learning for 3D Real-World Challengescited by 21
  36. 2021Detecting Anomalies in Semantic Segmentation with Prototypescited by 13
  37. 2021RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptationcited by 8
  38. 2020Empowering Knowledge Distillation via Open Set Recognition for Robust 3D Point Cloud Classificationcited by 6

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 1; 2025: 4; 2026: 2.

11 papers.

  1. 2023Open-Vocabulary Point-Cloud Object Detection without 3D Annotationcited by 81
  2. 2023OpenSight: A Simple Open-Vocabulary Framework for LiDAR-Based Object Detectioncited by 22
  3. 2022PointCaM: Cut-and-Mix for Open-Set Point Cloud Learningcited by 11
  4. 2024ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Drivingcited by 6
  5. 2022PartCom: Part Composition Learning for 3D Open-Set Recognitioncited by 1
  6. 2025Efficient Odd-One-Out Anomaly Detectioncited by 1
  7. 2026DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detectioncited by 1
  8. 2025SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Cloudscited by 0
  9. 2025SODA: Out-of-Distribution Detection in Domain-Shifted Point Clouds via Neighborhood Propagationcited by 0
  10. 2025Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagationcited by 0
  11. 2026Energy-Based Open-Set Active Learning for Object Classificationcited by 0