English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recently, 3D anomaly detection, a crucial problem involving fine-grainedgeometry discrimination, is getting more attention. However, the lack ofabundant real 3D anomaly data limits the scalability of current models. Toenable scalable anomaly data collection, we propose a 3D anomaly synthesispipeline to adapt existing large-scale 3Dmodels for 3D anomaly detection.Specifically, we construct a synthetic dataset, i.e., Anomaly-ShapeNet, basedonShapeNet. Anomaly-ShapeNet consists of 1600 point cloud samples under 40categories, which provides a rich and varied collection of data, enablingefficient training and enhancing adaptability to industrial scenarios.Meanwhile,to enable scalable representation learning for 3D anomalylocalization, we propose a self-supervised method, i.e., Iterative MaskReconstruction Network (IMRNet). During training, we propose a geometry-awaresample module to preserve potentially anomalous local regions during pointcloud down-sampling. Then, we randomly mask out point patches and sent thevisible patches to a transformer for reconstruction-based self-supervision.During testing, the point cloud repeatedly goes through the Mask ReconstructionNetwork, with each iteration's output becoming the next input. By merging andcontrasting the final reconstructed point cloud with the initial input, ourmethod successfully locates anomalies. Experiments show that IMRNet outperformsprevious state-of-the-art methods, achieving 66.1% in I-AUC on Anomaly-ShapeNetdataset and 72.5% in I-AUC on Real3D-AD dataset. Our dataset will be releasedat https://github.com/Chopper-233/Anomaly-ShapeNet

Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network