SOTAVerified

3D Anomaly Detection

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

Papers

Showing 125 of 36 papers

TitleStatusHype
Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial DefectsCode2
Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly DetectionCode2
PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly DetectionCode2
Multimodal Industrial Anomaly Detection via Hybrid FusionCode2
Towards Total Recall in Industrial Anomaly DetectionCode2
Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly DetectionCode1
R3D-AD: Reconstruction via Diffusion for 3D Anomaly DetectionCode1
Looking 3D: Anomaly Detection with 2D-3D AlignmentCode1
SplatPose & Detect: Pose-Agnostic 3D Anomaly DetectionCode1
Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning NetworkCode1
Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the LeadCode1
Real3D-AD: A Dataset of Point Cloud Anomaly DetectionCode1
Shape-Guided: Shape-Guided Dual-Memory Learning for 3D Anomaly DetectionCode1
Asymmetric Student-Teacher Networks for Industrial Anomaly DetectionCode1
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly DetectionCode1
Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection0
SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmark0
Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric RepresentationCode0
Mentor3AD: Feature Reconstruction-based 3D Anomaly Detection via Multi-modality Mentor Learning0
Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly DetectionCode0
MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detection0
Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving0
Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shift0
Fence Theorem: Preprocessing is Dual-Objective Semantic Structure Isolator in 3D Anomaly Detection0
Exploiting Point-Language Models with Dual-Prompts for 3D Anomaly Detection0
Show:102550
← PrevPage 1 of 2Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DUS-NetMean Performance of P. and O. 0.82Unverified
2MC4ADMean Performance of P. and O. 0.81Unverified
3ISMPMean Performance of P. and O. 0.8Unverified
4MC3D-ADMean Performance of P. and O. 0.78Unverified
5PASDFMean Performance of P. and O. 0.77Unverified
6PO3ADMean Performance of P. and O. 0.77Unverified
7Group3ADMean Performance of P. and O. 0.74Unverified
8PointADMean Performance of P. and O. 0.74Unverified
9IMRNetMean Performance of P. and O. 0.73Unverified
10GLFMMean Performance of P. and O. 0.72Unverified
#ModelMetricClaimedVerifiedStatus
1MC4ADO-AUROC0.91Unverified
2PASDFO-AUROC0.9Unverified
3MC3D-ADO-AUROC0.84Unverified
4PO3ADO-AUROC0.84Unverified
5DUS-NetO-AUROC0.8Unverified
6R3D-ADO-AUROC0.75Unverified
7ISMPO-AUROC0.71Unverified
8IMRNetO-AUROC0.66Unverified
#ModelMetricClaimedVerifiedStatus
1MC4ADO-AUROC0.89Unverified
2PatchCore (FPFH)O-AUROC0.88Unverified
3BTF (FPFH)O-AUROC0.63Unverified
4M3DMO-AUROC0.57Unverified
5PatchCore (PointMAE)O-AUROC0.57Unverified
6Reg3D-ADO-AUROC0.53Unverified
7BTF (Raw)O-AUROC0.5Unverified