mlsanityData to 7 Oct 2026

PC2-AD: Point Cloud Upsampling to Safeguard 3D Anomaly Detection with Resolution-constrained Edge Devices

arXiv 2609.14722 ↗First posted 13 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Low-cost and low-resolution sensors used in edge deployments can produce test point clouds that are substantially sparser than the normal training data. This train-test sampling-resolution gap changes the local geometry available to a 3D anomaly detector. We propose PC2-AD, a point cloud upsampling framework that compensates sparse test inputs before downstream detection. Target Domain Candidate Generation (TCG) adapts a pretrained upsampler to normal training geometry and generates a dense candidate pool. Geometry-Aware Candidate Filtering (GACF) selects candidates according to geometric spacing and spatial coverage. Normality-Preserving Point Compensation (NPPC) refines the selection by comparing candidate normality scores with those of their input anchors. The selected points are combined with the unchanged input points and processed by the existing detector. Experiments with six detectors on two Anomaly-ShapeNet settings and Real3D-AD show improvements in the mean of object-level and point-level AUROC for all six detectors in each Anomaly-ShapeNet setting and four on Real3D-AD. These results support point cloud compensation as an input-level approach to improving 3D anomaly detection under low-resolution sensing conditions. Code is publicly available at https://github.com/gyutong406-commits/PC2-AD.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 44 references that are in the map. First posted on arXiv 13 Sep 2026.

Builds on

33 of 44 references.

References · 33

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  5. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  6. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  7. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  8. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  9. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 138
  10. 2019PU-GCN: Point Cloud Upsampling using Graph Convolutional Networkscited by 100
  11. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 92
  12. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 87
21 more
  1. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  2. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 74
  3. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  4. 2024R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detectioncited by 45
  5. 2023Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functionscited by 43
  6. 2021PU-Transformer: Point Cloud Upsampling Transformercited by 32
  7. 2024PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detectioncited by 30
  8. 2024Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detectioncited by 30
  9. 2024SplatPose & Detect: Pose-Agnostic 3D Anomaly Detectioncited by 25
  10. 2024Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learningcited by 25
  11. 2025MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detectioncited by 23
  12. 2025Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly Detectioncited by 16
  13. 2025Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defectscited by 15
  14. 2025Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detectioncited by 11
  15. 2025Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric Representationcited by 9
  16. 2025Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detectioncited by 7
  17. 2025CASL: Curvature-Augmented Self-supervised Learning for 3D Anomaly Detectioncited by 5
  18. 2026Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspectivecited by 4
  19. 2025BridgeNet: A Unified Multimodal Framework for Bridging 2D and 3D Industrial Anomaly Detectioncited by 2
  20. 2026Multimodal Industrial Anomaly Detection via Geometric Priorcited by 1
  21. 2026Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detectioncited by 1

Built on by

Not cited yet.