mlsanityData to 7 Oct 2026

Cross-Modal Mapping and Dual-Branch Reconstruction for 2D-3D Multimodal Industrial Anomaly Detection

arXiv 2603.03939 ↗First posted 4 Mar 2026cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Multimodal industrial anomaly detection benefits from integrating RGB appearance with 3D surface geometry, yet existing unsupervised approaches commonly rely on memory banks, teacher-student architectures, or fragile fusion schemes, limiting robustness under noisy depth, weak texture, or missing modalities. This paper introduces CMDR-IAD, a lightweight and modality-flexible unsupervised framework for reliable anomaly detection in 2D+3D multimodal as well as single-modality (2D-only or 3D-only) settings. CMDR-IAD combines bidirectional 2Dleftrightarrow3D cross-modal mapping to model appearance-geometry consistency with dual-branch reconstruction that independently captures normal texture and geometric structure. A two-part fusion strategy integrates these cues: a reliability-gated mapping anomaly highlights spatially consistent texture-geometry discrepancies, while a confidence-weighted reconstruction anomaly adaptively balances appearance and geometric deviations, yielding stable and precise anomaly localization even in depth-sparse or low-texture regions. On the MVTec 3D-AD benchmark, CMDR-IAD achieves state-of-the-art performance while operating without memory banks, reaching 97.3% image-level AUROC (I-AUROC), 99.6% pixel-level AUROC (P-AUROC), and 97.6% AUPRO. On a real-world polyurethane cutting dataset, the 3D-only variant attains 92.6% I-AUROC and 92.5% P-AUROC, demonstrating strong effectiveness under practical industrial conditions. These results highlight the framework's robustness, modality flexibility, and the effectiveness of the proposed fusion strategies for industrial visual inspection. Our source code is available at https://github.com/ECGAI-Research/CMDR-IAD/

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 46 references that are in the map. First posted on arXiv 4 Mar 2026.

Builds on

28 of 46 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  6. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  7. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  8. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  9. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  10. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  11. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 174
  12. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
16 more
  1. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  2. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 138
  3. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  4. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  5. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 115
  6. 2020Deep Nearest Neighbor Anomaly Detectioncited by 103
  7. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 92
  8. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  9. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  10. 2022Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptorscited by 66
  11. 2020DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentationcited by 53
  12. 2023Multimodal Industrial Anomaly Detection by Crossmodal Feature Mappingcited by 41
  13. 2022Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samplescited by 12
  14. 2024Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspectivecited by 12
  15. 2022Composite Score for Anomaly Detection in Imbalanced Real-World Industrial Datasetcited by 7
  16. 2024Incomplete Multimodal Industrial Anomaly Detection via Cross-Modal Distillationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Robust Fault Detection in Mechanical Multimodal Time Series via Self-Supervised Cross-Modal Reconstructioncited by 0