mlsanityData to 7 Oct 2026

Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detection

arXiv 2505.05901 ↗First posted 9 May 2025cs.CV cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

In this paper, we explore a novel approach to 3D anomaly detection (AD) that goes beyond merely identifying anomalies based on structural characteristics. Our primary perspective is that most anomalies arise from unpredictable defective forces originating from both internal and external sources. To address these anomalies, we seek out opposing forces that can help correct them. Therefore, we introduce the Mechanics Complementary Model-based Framework for the 3D-AD task (MC4AD), which generates internal and external corrective forces for each point. We first propose a Diverse Anomaly-Generation (DA-Gen) module designed to simulate various types of anomalies. Next, we present the Corrective Force Prediction Network (CFP-Net), which uses complementary representations for point-level analysis to simulate the different contributions from internal and external corrective forces. To ensure the corrective forces are constrained effectively, we have developed a combined loss function that includes a new symmetric loss and an overall loss. Notably, we implement a Hierarchical Quality Control (HQC) strategy based on a three-way decision process and contribute a dataset titled Anomaly-IntraVariance, which incorporates intraclass variance to evaluate our model. As a result, the proposed MC4AD has been proven effective through theory and experimentation. The experimental results demonstrate that our approach yields nine state-of-the-art performances, achieving optimal results with minimal parameters and the fastest inference speed across five existing datasets, in addition to the proposed Anomaly-IntraVariance dataset. The source is available at https://github.com/hzzzzzhappy/MC4AD

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 45 of its 58 references that are in the map. First posted on arXiv 9 May 2025.

Builds on

45 of 58 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2020Point Transformercited by 1,462
  7. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  8. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  9. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  10. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  11. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  12. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
33 more
  1. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 174
  2. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
  3. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  4. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 138
  5. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 126
  6. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  7. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 92
  8. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  9. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 79
  10. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 74
  11. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  12. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  13. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  14. 2024R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detectioncited by 45
  15. 2024Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imaginationcited by 45
  16. 2023Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Leadcited by 40
  17. 2024PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detectioncited by 30
  18. 2024Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detectioncited by 30
  19. 2024PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detectioncited by 29
  20. 2024SplatPose & Detect: Pose-Agnostic 3D Anomaly Detectioncited by 25
  21. 2024Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learningcited by 25
  22. 2021AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learningcited by 21
  23. 2025Exploring the Potential of Encoder-free Architectures in 3D LMMscited by 16
  24. 2024Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Frameworkcited by 15
  25. 2024Looking 3D: Anomaly Detection with 2D-3D Alignmentcited by 13
  26. 2024SplatPose+: Real-time Image-Based Pose-Agnostic 3D Anomaly Detectioncited by 11
  27. 2024Towards Zero-shot 3D Anomaly Localizationcited by 8
  28. 2022Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classicscited by 5
  29. 2025Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shiftcited by 5
  30. 2025Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detectioncited by 4
  31. 20253D-PNAS: 3D Industrial Surface Anomaly Synthesis with Perlin Noisecited by 2
  32. 2025A 3D Multimodal Feature for Infrastructure Anomaly Detectioncited by 1
  33. 2025Deep Subspace Learning for Surface Anomaly Classification Based on 3D Point Cloud Datacited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025PointAD+: Learning Hierarchical Representations for Zero-shot 3D Anomaly Detectioncited by 1
  2. 2025Mentor3AD: Feature Reconstruction-based 3D Anomaly Detection via Multi-modality Mentor Learningcited by 0
  3. 2026Synthesis4AD: Synthetic Anomalies are All You Need for 3D Anomaly Detectioncited by 0
  4. 2026Point Cloud Diffusion with Global and Local Reconstruction for Instance-Level 3D Anomaly Detectioncited by 0