mlsanityData to 7 Oct 2026

Looking 3D: Anomaly Detection with 2D-3D Alignment

arXiv 2406.19393 ↗First posted 27 Jun 2024cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Automatic anomaly detection based on visual cues holds practical significance in various domains, such as manufacturing and product quality assessment. This paper introduces a new conditional anomaly detection problem, which involves identifying anomalies in a query image by comparing it to a reference shape. To address this challenge, we have created a large dataset, BrokenChairs-180K, consisting of around 180K images, with diverse anomalies, geometries, and textures paired with 8,143 reference 3D shapes. To tackle this task, we have proposed a novel transformer-based approach that explicitly learns the correspondence between the query image and reference 3D shape via feature alignment and leverages a customized attention mechanism for anomaly detection. Our approach has been rigorously evaluated through comprehensive experiments, serving as a benchmark for future research in this domain.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 21 of its 39 references that are in the map. First posted on arXiv 27 Jun 2024.

Builds on

21 of 39 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2023Segment Anythingcited by 8,158
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  6. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  7. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  8. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  9. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  10. 2019The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentationcited by 122
  11. 2018Anomaly Detection using One-Class Neural Networkscited by 82
  12. 2021KVT: k-NN Attention for Boosting Vision Transformerscited by 64
9 more
  1. 20192D3D-MatchNet: Learning to Match Keypoints Across 2D Image and 3D Point Cloudcited by 62
  2. 2019Detecting semantic anomaliescited by 50
  3. 2023PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detectioncited by 46
  4. 20183D Pose Estimation and 3D Model Retrieval for Objects in the Wildcited by 31
  5. 2019LCD: Learned Cross-Domain Descriptors for 2D-3D Matchingcited by 29
  6. 20232D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Cloudscited by 27
  7. 2018PhotoShape: Photorealistic Materials for Large-Scale Shape Collectionscited by 21
  8. 2019Location Field Descriptors: Single Image 3D Model Retrieval in the Wildcited by 15
  9. 2022DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repaircited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 5.

13 papers.

Sort:

By area:

  1. 2024Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detectioncited by 30
  2. 2025Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detectioncited by 11
  3. 2025A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Featurescited by 5
  4. 2024Odd-One-Out: Anomaly Detection by Comparing with Neighborscited by 4
  5. 2025Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detectioncited by 4
  6. 2025Out-of-Distribution Semantic Occupancy Predictioncited by 2
  7. 2025Efficient Odd-One-Out Anomaly Detectioncited by 1
  8. 2025Mentor3AD: Feature Reconstruction-based 3D Anomaly Detection via Multi-modality Mentor Learningcited by 0
  9. 2026BAAF: Universal Transformation of One-Class Classifiers for Unsupervised Image Anomaly Detectioncited by 0
  10. 2026Open-Set Supervised 3D Anomaly Detection: An Industrial Dataset and a Generalisable Framework for Unknown Defectscited by 0
  11. 2026Learning Discriminative Signed Distance Functions from Multi-scale Level-of-detail Features for 3D Anomaly Detectioncited by 0
  12. 2026MATCH: Flow Matching for Multi-View Anomaly Detectioncited by 0
1 more
  1. 2026LTM: Large-scale Terrain Model for Wildfire-prone Landscapescited by 0