OpenCodePapers
3d-anomaly-detection-on-real-3d-ad
3D Anomaly Detection
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
Mean Performance of P. and O.
↕
Point AUROC
↕
Object AUROC
↕
ModelName
ReleaseDate
↕
Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection
0.821
0.847
0.795
DUS-Net
2025-07-05
Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detection
✓ Link
0.8115
0.837
0.786
MC4AD
2025-05-09
Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detection
✓ Link
0.7965
0.836
0.757
ISMP
2024-12-18
MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detection
0.775
0.768
0.782
MC3D-AD
2025-05-04
Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric Representation
0.7735
0.745
0.802
PASDF
2025-05-30
PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection
0.765
0.765
PO3AD
2024-12-17
Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning
0.743
0.735
0.751
Group3AD
2024-08-08
PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection
✓ Link
0.7375
0.716
0.759
PointAD
2024-10-01
Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network
✓ Link
0.725
0.725
IMRNet
2023-11-25
Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly Detection
✓ Link
0.715
0.898
0.532
GLFM
2025-02-21
Real3D-AD: A Dataset of Point Cloud Anomaly Detection
✓ Link
0.702
0.700
0.704
Reg3D-AD
2023-09-23
Towards Total Recall in Industrial Anomaly Detection
✓ Link
0.687
0.692
0.682
PatchCore (FPFH+Raw)
2021-06-15
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection
✓ Link
0.6785
0.722
0.635
BTF (Raw)
2022-03-10
R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection
✓ Link
0.663
0.592
0.734
R3D-AD
2024-07-15
Towards Total Recall in Industrial Anomaly Detection
✓ Link
0.614
0.634
0.594
PatchCore (PointMAE)
2021-06-15
Multimodal Industrial Anomaly Detection via Hybrid Fusion
✓ Link
0.5945
0.637
0.552
M3DM (PointMAE)
2023-03-01
Towards Total Recall in Industrial Anomaly Detection
✓ Link
0.5925
0.592
0.593
PatchCore (FPFH)
2021-06-15
Multimodal Industrial Anomaly Detection via Hybrid Fusion
✓ Link
0.587
0.636
0.538
M3DM (PointBERT)
2023-03-01
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection
✓ Link
0.5845
0.566
0.603
BTF (FPFH)
2022-03-10