Abstract
Automated detection of surface defects on three-dimensional (3D) parts is vital for ensuring product quality and safety in manufacturing. However, three key challenges hinder reliable detection: geometric context ambiguity across complex part shapes, domain mismatch between generic pretrained features and industrial scans (with their unique noise and reflectivity), and the scarcity of diverse defect examples for training. To overcome these issues, we propose a novel single-forward-pass framework for point cloud anomaly detection, comprising three new modules: (1) Spatial Context Aggregation, which grounds each local patch in a set of learned global prototypes via an optimal-transport alignment to resolve context ambiguity; (2) Feature Adaptor, a lightweight two-layer multilayer perceptron (MLP) that fine-tunes self-supervised Point-MAE embeddings to the specific characteristics of industrial scans; and (3) Selective Anomalous Feature Generator, which synthesizes realistic hard negatives by corrupting random subsets of feature tokens, thus mitigating the need for extensive defect labels. An attention-based discriminator trained with patch-wise supervision learns to distinguish these hard negatives from genuine defect-free patterns. At inference, our pipeline delivers dense per-point anomaly scores in a single pass at up to 13.5 frames per second (FPS). On the Real3D-AD benchmark, we observe point-level improvements of 2.8% in area under the receiver operating characteristic curve (AUROC) and 5.7% in area under the precision-recall curve (AUPR), with object-level gains of 3.0% (AUROC) and 3.5% (AUPR). Evaluated on our newly released Industrial3D-AD dataset, which captures realistic sensor noise and reflective materials, we see similar enhancements (2.9%/5.3% point-level, 2.8%/3.3% object-level).
Data availability
The newly collected Industrial3D-AD dataset used and analyzed during the current study are available from the corresponding author on reasonable request. The Real3D-AD dataset is accessible on GitHub at https://github.com/M-3LAB/Real3D-AD.
References
Pu, C. et al. Geometric spatial constraints network for slender and tiny surface defect detection. Adv. Eng. Inform. 65, 103138 (2025).
Ma, X. et al. Stamping part surface crack detection based on machine vision. Measurement 251, 117168 (2025).
Hoang, D.-C. et al. Unsupervised industrial anomaly detection using paired well-lit and low-light images. J. Comput. Des. Eng. 12, 41–61 (2025).
Zhang, K. et al. Automatic measurement system for aircraft rivet flushness on surfaces empowered by multi-modal large-scale models. Adv. Eng. Inform. 69, 103936 (2026).
Egodawela, S. et al. Metal loss defect detection and depth estimation using multi-spectral image analysis of cooling excited steel specimen with corrosion. Sci. Rep. 15, 23894 (2025).
Hoang, D.-C. et al. Unsupervised visual-to-geometric feature reconstruction for vision-based industrial anomaly detection. IEEE Access. (2025).
Tong, X. et al. Dam-faster RCNN: few-shot defect detection method for wood based on dual attention mechanism. Sci. Rep. 15, 22860 (2025).
Hoang, D.-C. et al. Image-based anomaly detection in low-light industrial environments with feature enhancement. Results Eng. 25, 104309 (2025).
Zhang, C., Guo, Z. & Li, C. Unsupervised anomaly detection for gearboxes based on the deep convolutional support generative adversarial network. Sci. Rep. 15, 20977 (2025).
Song, H. Rstd-yolov7: a steel surface defect detection based on improved yolov7. Sci. Rep. 15, 19649 (2025).
Bergmann, P., Fauser, M., Sattlegger, D. & Steger, C. Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 4183–4192 (2020).
Shi, Y., Yang, J. & Qi, Z. DFR: Deep feature reconstruction for unsupervised anomaly segmentation. Neurocomputing 424, 9–22 (2021).
Roth, K. et al. Towards total recall in industrial anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 14318–14328 (2022).
Hoang, D.-C. et al. Accurate industrial anomaly detection with efficient multimodal fusion. Array 100512 (2025).
Horwitz, E. & Hoshen, Y. Back to the feature: classical 3d features are (almost) all you need for 3d anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2968–2977 (2023).
Bergmann, P. & Sattlegger, D. Anomaly detection in 3d point clouds using deep geometric descriptors. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2613–2623 (2023).
Liu, J. et al. Real3D-AD: A dataset of point cloud anomaly detection. Adv. Neural. Inf. Process. Syst. 36, 30402–30415 (2023).
Zhu, H. et al. Towards high-resolution 3d anomaly detection via group-level feature contrastive learning. In Proceedings of the 32nd ACM International Conference on Multimedia, 4680–4689 (2024).
Li, W. et al. Towards scalable 3d anomaly detection and localization: A benchmark via 3d anomaly synthesis and a self-supervised learning network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 22207–22216 (2024).
Zhou, Z. et al. R3D-AD: Reconstruction via diffusion for 3d anomaly detection. In European Conference on Computer Vision, 91–107 (Springer, 2024).
Venkataramanan, S., Peng, K.-C., Singh, R. V. & Mahalanobis, A. Attention guided anomaly localization in images. In European Conference on Computer Vision, 485–503 (Springer, 2020).
Ding, C., Pang, G. & Shen, C. Catching both gray and black swans: Open-set supervised anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 7388–7398 (2022).
Chadha, G. S., Rabbani, A. & Schwung, A. Comparison of semi-supervised deep neural networks for anomaly detection in industrial processes. In 2019 IEEE 17th International Conference on Industrial Informatics (INDIN), vol. 1, 214–219 (IEEE, 2019).
Chu, W.-H. & Kitani, K. M. Neural batch sampling with reinforcement learning for semi-supervised anomaly detection. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXVI 16, 751–766 (Springer, 2020).
Gu, Z. et al. Remembering normality: Memory-guided knowledge distillation for unsupervised anomaly detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 16401–16409 (2023).
Tong, G., Li, Q. & Song, Y. Enhanced multi-scale features mutual mapping fusion based on reverse knowledge distillation for industrial anomaly detection and localization. IEEE Trans. Big Data 10, 498–513 (2024).
Hou, J. et al. Divide-and-Assemble: Learning block-wise memory for unsupervised anomaly detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 8791–8800 (2021).
Zavrtanik, V., Kristan, M. & Skočaj, D. DRAEM-a discriminatively trained reconstruction embedding for surface anomaly detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 8330–8339 (2021).
Zavrtanik, V., Kristan, M. & Skočaj, D. DSR-a dual subspace re-projection network for surface anomaly detection. In European Conference on Computer Vision, 539–554 (Springer, 2022).
Fang, Z. et al. FastRecon: Few-shot industrial anomaly detection via fast feature reconstruction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 17481–17490 (2023).
Zhang, X., Xu, M. & Zhou, X. RealNet: A feature selection network with realistic synthetic anomaly for anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16699–16708 (2024).
Yan, X., Zhang, H., Xu, X., Hu, X. & Heng, P.-A. Learning semantic context from normal samples for unsupervised anomaly detection. In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, 3110–3118 (2021).
Song, J., Kong, K., Park, Y.-I., Kim, S.-G. & Kang, S.-J. AnoSeg: Anomaly segmentation network using self-supervised learning. arXiv preprint arXiv:2110.03396 (2021).
Liang, Y. et al. Omni-frequency channel-selection representations for unsupervised anomaly detection. IEEE Trans. Image Process. 32, 4327–4340 (2023).
De Nardin, A., Mishra, P., Foresti, G. L. & Piciarelli, C. Masked transformer for image anomaly localization. Int. J. Neural Syst. 32, 2250030 (2022).
Yao, X., Li, R., Qian, Z., Luo, Y. & Zhang, C. Focus the discrepancy: Intra-and inter-correlation learning for image anomaly detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 6803–6813 (2023).
Luo, W., Yao, H., Yu, W. & Li, Z. AMI-Net: Adaptive mask inpainting network for industrial anomaly detection and localization. IEEE Trans. Autom. Sci. Eng. (2024).
Zhang, X. et al. Unsupervised surface anomaly detection with diffusion probabilistic model. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 6782–6791 (2023).
Lu, F., Yao, X., Fu, C.-W. & Jia, J. Removing anomalies as noises for industrial defect localization. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 16166–16175 (2023).
Tebbe, J. & Tayyub, J. Dynamic addition of noise in a diffusion model for anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 3940–3949 (2024).
Salehi, M., Sadjadi, N., Baselizadeh, S., Rohban, M. H. & Rabiee, H. R. Multiresolution knowledge distillation for anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 14902–14912 (2021).
Wan, Q., Gao, L., Li, X. & Wen, L. Unsupervised image anomaly detection and segmentation based on pretrained feature mapping. IEEE Trans. Industr. Inf. 19, 2330–2339 (2022).
Defard, T., Setkov, A., Loesch, A. & Audigier, R. PaDiM: a patch distribution modeling framework for anomaly detection and localization. In International Conference on Pattern Recognition, 475–489 (Springer, 2021).
Bae, J., Lee, J.-H. & Kim, S. PNI: Industrial anomaly detection using position and neighborhood information. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 6373–6383 (2023).
Zuo, Z., Wu, Z., Chen, B. & Zhong, X. A reconstruction-based feature adaptation for anomaly detection with self-supervised multi-scale aggregation. In ICASSP 2024–2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 5840–5844 (IEEE, 2024).
Hyun, J. et al. ReConPatch: Contrastive patch representation learning for industrial anomaly detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2052–2061 (2024).
Li, C.-L., Sohn, K., Yoon, J. & Pfister, T. CutPaste: Self-supervised learning for anomaly detection and localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9664–9674 (2021).
Liu, Z., Zhou, Y., Xu, Y. & Wang, Z. SimpleNet: A simple network for image anomaly detection and localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 20402–20411 (2023).
Cao, Y., Xu, X. & Shen, W. Complementary pseudo multimodal feature for point cloud anomaly detection. Pattern Recogn. 156, 110761 (2024).
Wang, Y. et al. Multimodal industrial anomaly detection via hybrid fusion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8032–8041 (2023).
Rudolph, M., Wehrbein, T., Rosenhahn, B. & Wandt, B. Asymmetric student-teacher networks for industrial anomaly detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2592–2602 (2023).
Pang, Y. et al. Masked autoencoders for point cloud self-supervised learning. In European Conference on Computer Vision, 604–621 (Springer, 2022).
Chang, A. X. et al. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012 (2015).
Peyré, G. et al. Computational optimal transport: With applications to data science. Found. Trends Mach. Learn. 11, 355–607 (2019).
Rusu, R. B., Blodow, N. & Beetz, M. Fast point feature histograms (FPFH) for 3d registration. In 2009 IEEE International Conference on Robotics and Automation, 3212–3217 (IEEE, 2009).
Yu, X. et al. Point-BERT: Pre-training 3d point cloud transformers with masked point modeling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 19313–19322 (2022).
Funding
This research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.
Author information
Authors and Affiliations
Contributions
All authors contributed equally to the conceptualization, formal analysis, investigation, methodology, and writing and editing of the original draft. All authors have read and agreed to the published version of the manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Hoang, DC., Tan, P.X., Nguyen, AN. et al. Efficient industrial point cloud anomaly detection via spatial context aggregation and selective anomalous feature generation. Sci Rep (2026). https://doi.org/10.1038/s41598-026-41255-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-41255-2
