HyperAI초신경

Depth Anomaly Detection And Segmentation On

평가 지표

Detection AUROC
Segmentation AUPRO
Segmentation AUROC

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Detection AUROC
Segmentation AUPRO
Segmentation AUROC
Paper TitleRepository
CPMF (2D)0.89180.91450.9730Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection
TransFusion0.9570.947-TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection
Depth VM0.5460.374-The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization
CPMF (2D+3D)0.95150.92930.9781Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection
CPMF (3D)0.83040.92300.9780Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (Depth iNet)0.6750.7550.930Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (SIFT)0.7270.9100.974Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (RaW)0.5730.4420.771Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection
3DSR (3D)0.9220.907-Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (NSA)0.6960.55720.817Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection
Depth GAN0.5230.143-The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization
Depth AE0.5460.203-The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (HoG)0.5590.7710.930Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection
0 of 13 row(s) selected.