SOTAVerified

3D Anomaly Detection

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

Papers

Showing 1–36 of 36 papers

TitleStatusHype
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
Towards Total Recall in Industrial Anomaly DetectionCode2
Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial DefectsCode2
Multimodal Industrial Anomaly Detection via Hybrid FusionCode2
SplatPose & Detect: Pose-Agnostic 3D Anomaly DetectionCode1
Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the LeadCode1
Looking 3D: Anomaly Detection with 2D-3D AlignmentCode1
Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly DetectionCode1
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly DetectionCode1
Asymmetric Student-Teacher Networks for Industrial Anomaly DetectionCode1
Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning NetworkCode1
R3D-AD: Reconstruction via Diffusion for 3D Anomaly DetectionCode1
Real3D-AD: A Dataset of Point Cloud Anomaly DetectionCode1
Shape-Guided: Shape-Guided Dual-Memory Learning for 3D Anomaly DetectionCode1
Uni-3DAD: GAN-Inversion Aided Universal 3D Anomaly Detection on Model-free Products—0
Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptors—0
DAS3D: Dual-modality Anomaly Synthesis for 3D Anomaly Detection—0
EasyNet: An Easy Network for 3D Industrial Anomaly Detection—0
Exploiting Point-Language Models with Dual-Prompts for 3D Anomaly Detection—0
Fence Theorem: Preprocessing is Dual-Objective Semantic Structure Isolator in 3D Anomaly Detection—0
MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detection—0
Mentor3AD: Feature Reconstruction-based 3D Anomaly Detection via Multi-modality Mentor Learning—0
PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection—0
Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shift—0
SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmark—0
Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving—0
Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection—0
Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samples—0
Towards Zero-shot 3D Anomaly Localization—0
3D-CSAD: Untrained 3D Anomaly Detection for Complex Manufacturing Surfaces—0
Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural PerspectiveCode0
Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly DetectionCode0
Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric RepresentationCode0
SplatPose+: Real-time Image-Based Pose-Agnostic 3D Anomaly DetectionCode0
Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive LearningCode0
Show:102550

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DUS-NetMean Performance of P. and O. 0.82—Unverified
2MC4ADMean Performance of P. and O. 0.81—Unverified
3ISMPMean Performance of P. and O. 0.8—Unverified
4MC3D-ADMean Performance of P. and O. 0.78—Unverified
5PASDFMean Performance of P. and O. 0.77—Unverified
6PO3ADMean Performance of P. and O. 0.77—Unverified
7Group3ADMean Performance of P. and O. 0.74—Unverified
8PointADMean Performance of P. and O. 0.74—Unverified
9IMRNetMean Performance of P. and O. 0.73—Unverified
10GLFMMean Performance of P. and O. 0.72—Unverified
#ModelMetricClaimedVerifiedStatus
1MC4ADO-AUROC0.91—Unverified
2PASDFO-AUROC0.9—Unverified
3MC3D-ADO-AUROC0.84—Unverified
4PO3ADO-AUROC0.84—Unverified
5DUS-NetO-AUROC0.8—Unverified
6R3D-ADO-AUROC0.75—Unverified
7ISMPO-AUROC0.71—Unverified
8IMRNetO-AUROC0.66—Unverified
#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