Rgb 3D Anomaly Detection And Segmentation On
평가 지표
Detection AUCROC
Segmentation AUPRO
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Detection AUCROC | Segmentation AUPRO | Paper Title | Repository |
|---|---|---|---|---|
| Voxel GAN | 0.517 | 0.639 | 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 (BTF) | 0.865 | 0.959 | Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection | |
| Shape-Guided | 0.947 | 0.976 | Shape-Guided: Shape-Guided Dual-Memory Learning for 3D Anomaly Detection | |
| 3DSR | 0.978 | 0.972 | Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation | |
| Voxel AE | 0.538 | 0.564 | The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization | |
| Voxel VM | 0.609 | 0.471 | The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization | |
| M3DM | 0.945 | 0.964 | Multimodal Industrial Anomaly Detection via Hybrid Fusion | |
| AST | 0.937 | - | Asymmetric Student-Teacher Networks for Industrial Anomaly Detection | |
| TransFusion | 0.982 | 0.983 | TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection |
0 of 9 row(s) selected.