mlsanityData to 14 Oct 2026

Point Cloud Novelty Detection Based on Latent Representations of a General Feature Extractor

arXiv 2410.09861 ↗First posted 13 Oct 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose an effective unsupervised 3D point cloud novelty detection approach, leveraging a general point cloud feature extractor and a one-class classifier. The general feature extractor consists of a graph-based autoencoder and is trained once on a point cloud dataset such as a mathematically generated fractal 3D point cloud dataset that is independent of normal/abnormal categories. The input point clouds are first converted into latent vectors by the general feature extractor, and then one-class classification is performed on the latent vectors. Compared to existing methods measuring the reconstruction error in 3D coordinate space, our approach utilizes latent representations where the shape information is condensed, which allows more direct and effective novelty detection. We confirm that our general feature extractor can extract shape features of unseen categories, eliminating the need for autoencoder re-training and reducing the computational burden. We validate the performance of our method through experiments on several subsets of the ShapeNet dataset and demonstrate that our latent-based approach outperforms the existing methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 40 references that are in the map. First posted on arXiv 13 Oct 2024.

Builds on

22 of 40 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  6. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  7. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  8. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 504
  9. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  10. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  11. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  12. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
10 more
  1. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  2. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  3. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  4. 2020Self-Supervised Learning for Domain Adaptation on Point-Cloudscited by 99
  5. 2019Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Predictioncited by 66
  6. 2019GODS: Generalized One-class Discriminative Subspaces for Anomaly Detectioncited by 64
  7. 2020SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimizationcited by 26
  8. 2020DPDist : Comparing Point Clouds Using Deep Point Cloud Distancecited by 22
  9. 2023Toward Unsupervised 3D Point Cloud Anomaly Detection using Variational Autoencodercited by 18
  10. 2022Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samplescited by 12

Built on by

Not cited yet.