Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection

Cao, Yunkang; Xu, Xiaohao; Shen, Weiming

doi:10.48550/arxiv.2303.13194

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The M3DM framework [39] innovatively combines 3D point data with conventional imaging for enhanced decision-making. CPMF [8] introduced a novel methodology that integrates a memory bank approach with KNN and enriches the detection process by rendering 3D data into multi-view 2D images. Conversely, EasyNet [12] presents a straightforward mechanism for 3D anomaly detection, circumventing the need for pre-training.…”

Section: Related Workmentioning

confidence: 99%

“…These factors make it challenging to apply reconstruction-based [3] or deep learning feature extraction-based [1] algorithms widely. Secondly, the prevailing approaches for point cloud anomaly detection heavily rely on traditional feature processing operators and models that are pretrained to extract features or transform data to 2D for processing [1,8]. This approach fails to fully exploit the potential of point cloud data and leads to significant feature domain misalignment.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Critique of “A Parallel Framework for Constraint-Based Bayesian Network Learning via Markov Blanket Discovery” by SCC Team From ShanghaiTech University

Cao

Zhao

et al. 2023

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

Recently, 3D anomaly detection, a crucial problem involving fine-grained geometry discrimination, is getting more attention. However, the lack of abundant real 3D anomaly data limits the scalability of current models. To enable scalable anomaly data collection, we propose a 3D anomaly synthesis pipeline to adapt existing large-scale 3D models for 3D anomaly detection. Specifically, we construct a synthetic dataset, i.e., Anomaly-ShapeNet, based on ShapeNet. Anomaly-ShapeNet consists of 1600 point cloud samples under 40 categories, which provides a rich and varied collection of data, enabling efficient training and enhancing adaptability to industrial scenarios. Meanwhile, to enable scalable representation learning for 3D anomaly localization, we propose a self-supervised method, i.e., Iterative Mask Reconstruction Network (IMRNet). During training, we propose a geometry-aware sample module to preserve potentially anomalous local regions during point cloud down-sampling. Then, we randomly mask out point patches and sent the visible patches to a transformer for reconstruction-based self-supervision. During testing, the point cloud repeatedly goes through the Mask Reconstruction Network, with each iteration's output becoming the next input. By merging and contrasting the final reconstructed point cloud with the initial input, our method successfully locates anomalies. Experiments show that IMR-Net outperforms previous state-of-the-art methods, achieving 66.1% in I-AUC on Anomaly-ShapeNet dataset and 72.5% in I-AUC on Real3D-AD dataset. Our dataset will be released at https://github.com/Chopper-233/Anomaly-ShapeNet.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Critique of “A Parallel Framework for Constraint-Based Bayesian Network Learning via Markov Blanket Discovery” by SCC Team From ShanghaiTech University

Cao

Zhao

et al. 2023

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

show abstract

“…Consequently, many tasks [11][12][13] are moving toward unsupervised methods based on MVTec AD [14] to carry out surface defect detection. Furthermore, several tasks [15,16] have emerged employing MVTec 3D-AD [17] for three-dimensional (3D) defect detection. These methods only need to learn the distribution of the normal training data and samples that do not belong to the normal training data distribution are labeled as abnormal during inference.…”

Section: Introductionmentioning

confidence: 99%

Back to Michelson interferometer: a precise inspection system for industrial intricate structures defect detection

Xu,

Gu,

Gao

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Quality inspection of injection molding products with intricate three-dimensional structures and diffuse reflection characteristics is a very important procedure in industrial production. However, the current inspection process for these products still heavily relies on visual inspection, which introduces various issues including low efficiency, and missing or false detection. While previous studies have utilized deep-learning methods in conjunction with specific optical sensors and imaging systems to detect defects, the intricate structure of injection molding products and the small magnitude of defects pose significant challenges in defect detection. To address these challenges, this paper proposes an inspection system based on Michelson interferometer capable of detecting and characterizing defects of injection molding products. Notably, by utilizing the light intensity modulation and an improved image differencing approach, this inspection system is capable of detecting defects with a magnitude as small as 0.1 mm and achieving a remarkable detection accuracy exceeding 93% on self-made datasets without utilizing phase information. The effectiveness of our method is validated by comparison with mainstream deep-learning-based defect detection methods and visual inspection methods.

show abstract

Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection

Cited by 2 publications

References 0 publications

Critique of “A Parallel Framework for Constraint-Based Bayesian Network Learning via Markov Blanket Discovery” by SCC Team From ShanghaiTech University

Critique of “A Parallel Framework for Constraint-Based Bayesian Network Learning via Markov Blanket Discovery” by SCC Team From ShanghaiTech University

Back to Michelson interferometer: a precise inspection system for industrial intricate structures defect detection

Contact Info

Product

Resources

About