SOTAVerified

3D Anomaly Detection

3D-only Anomaly Detection. Structures out of normal distribution are detected from the 3D-only point cloud.

Papers

Showing 1–10 of 36 papers

TitleStatusHype
Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial DefectsCode2
Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection—0
SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmark—0
Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric RepresentationCode0
Mentor3AD: Feature Reconstruction-based 3D Anomaly Detection via Multi-modality Mentor Learning—0
Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly DetectionCode0
Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving—0
MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detection—0
Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shift—0
Fence Theorem: Preprocessing is Dual-Objective Semantic Structure Isolator in 3D Anomaly Detection—0
Show:102550
← PrevPage 1 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MC4ADO-AUROC0.89—Unverified
2PatchCore (FPFH)O-AUROC0.88—Unverified
3BTF (FPFH)O-AUROC0.63—Unverified
4M3DMO-AUROC0.57—Unverified
5PatchCore (PointMAE)O-AUROC0.57—Unverified
6Reg3D-ADO-AUROC0.53—Unverified
7BTF (Raw)O-AUROC0.5—Unverified