Research map / Label-efficient and robust learning / OOD and anomaly detection
Learning Diffusion Models for Multi-View Anomaly Detection
Chieh Liu, Yu-Min Chu, Ting-I Hsieh, Hwann-Tzong Chen, Tyng-Luh Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train with a view-invariant ControlNet instead of UNet only (ablation) | Diffusion-feature anomaly detector · Eyecandies (RGB+3D) | Img-ROC: 0.934 -> 0.948 | Improved |
| add feature consistency loss across the six views (ablation) | view-invariant ControlNet · Eyecandies (RGB+3D) | Img-ROC: 0.934 -> 0.948 | Improved |
| use decoder block-1 features only rather than blocks 1,2,3 (ablation) | diffusion feature memory bank · Eyecandies (RGB+3D) | Img-ROC: 0.868 -> 0.948 | Improved |
| increase noise intensity in DDIM inversion (ablation) | diffusion feature extraction · Eyecandies | Img-AUROC | Improved |
| replace UNet with ControlNet for the Nmap-only branch (ablation) | Nmap features · Eyecandies (Nmap) | Pix-ROC: 0.924 -> 0.828 | Hurt |
| fuse RGB and 3D normal score maps | multi-view anomaly detector · Eyecandies | Img-AUROC: 0.888 -> 0.948 | Improved |
| apply PatchCore re-weighting | scoring · Eyecandies | Img-AUROC | No clear effect |
Closest papers by meaning
- Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection (CVPR 2025 · similarity 0.89)
- A Diffusion-Based Framework for Multi-Class Anomaly Detection (AAAI 2024 · similarity 0.88)
- Unseen Visual Anomaly Generation (CVPR 2025 · similarity 0.88)
- AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model (AAAI 2024 · similarity 0.88)
- Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation (CVPR 2025 · similarity 0.88)
- Unveiling Multi-View Anomaly Detection: Intra-view Decoupling and Inter-view Fusion (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
