mlsanityData to 14 Oct 2026

MVFM-3DAD: Multi-view Flow Matching for 3D Anomaly Detection via Density Proxy Estimation

arXiv 2608.12148 ↗First posted 12 Aug 2026cs.GRcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

In 3D anomaly detection (3DAD), most existing methods rely on Memory bank retrieval or reconstruction. However, memory-based methods are constrained by the coverage of stored normal features, while reconstruction-based methods may learn identity shortcuts that also reconstruct anomalous inputs well. These limitations motivate a density-oriented approach that evaluates whether a test sample follows the learned normal distribution. To this end, we propose MVFM-3DAD, a flow-based framework that reframes 3DAD as density proxy estimation over the normal data distribution. MVFM-3DAD introduces a Bidirectional Geometric Projector (BGP), whose forward process converts irregular point clouds into structured multi-view representations. The Flow-guided Density Proxy Estimator (FDPE) estimates a reference density for each view feature, after which the backward process of BGP maps these multi-view density estimates to their corresponding 3D points. Building on it, anomalous features can be identified by their terminal normality. Unlike conventional flow-based likelihood estimation, our formulation requires neither input reconstruction nor explicit Jacobian evaluation, yielding a simple and efficient anomaly-scoring mechanism. Extensive experiments show that MVFM-3DAD outperforms the strongest competing methods on Real3D-AD and MVTec3D-AD. Code is available at https://github.com/lil-wayne-0319/MV3D-AD

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 25 of its 33 references that are in the map. First posted on arXiv 12 Aug 2026.

Builds on

25 of 33 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models21 May
  2. 2025Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching21 Oct
  3. 2025InvAD: Inversion-based Reconstruction-Free Anomaly Detection with Diffusion Models8 Apr

Other references · 22

  1. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  2. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  3. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  4. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 227
  5. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  6. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  7. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 93
  8. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  9. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 75
  10. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  11. 2024R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detectioncited by 45
  12. 2023EasyNet: An Easy Network for 3D Industrial Anomaly Detectioncited by 43
10 more
  1. 2023Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulationcited by 33
  2. 2024Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detectioncited by 30
  3. 2024PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detectioncited by 29
  4. 2023MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detectioncited by 25
  5. 2024M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoisingcited by 24
  6. 2024Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspectivecited by 12
  7. 2025Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detectioncited by 11
  8. 2025CASL: Curvature-Augmented Self-supervised Learning for 3D Anomaly Detectioncited by 5
  9. 2025A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Featurescited by 5
  10. 2026A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detectioncited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026MATCH: Flow Matching for Multi-View Anomaly Detection
  2. 2026Synthesis4AD: Synthetic Anomalies are All You Need for 3D Anomaly Detection
  3. 2026Two Steps Are All You Need: Efficient 3D Point Cloud Anomaly Detection with Consistency Models
  4. 2026Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection
  5. 2025Time-reversed Flow Matching with Worst Transport in High-dimensional Latent Space for Image Anomaly Detection
  6. 2026Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modeling
  7. 2025Unsupervised Multi-View Visual Anomaly Detection via Progressive Homography-Guided Alignment
  8. 2026Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection