AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attribution

Chaoran Xu, Chengkan Lv, Qiyu Chen, Yunkang Cao, Feng Zhang, Zhengtao Zhang

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
add latent-mask inpainting in late denoising (ablation)DeltaDeno · MVTec AD downstream detectionimage AUROC: 79.7 -> 84.7Improved
add latent-mask inpainting in late denoising (ablation)DeltaDeno · MVTec AD downstream detectionpixel AP: 25.8 -> 30.5Improved
add spatial attention biasing (ablation)DeltaDeno · MVTec AD downstream detectionimage AUROC: 79.5 -> 84.7Improved
add token-level prompt refinement (ablation)DeltaDeno · MVTec AD downstream detectionimage AUROC: 78.8 -> 84.7Improved
add SAM foreground prior (ablation)DeltaDeno · MVTec AD downstream detectionpixel AUROC: 82.1 -> 84.9Improved
switch backbone from SD1.5 to FLUXDeltaDeno · MVTec AD downstream detectionimage AUROC: 84.7 -> 89.7Improved
switch backbone from SD1.5 to FLUXDeltaDeno · VisA downstream detectionpixel AUROC: 90.1 -> 90.2No clear effect
raise t_mid threshold from 0.6 to 0.8 (ablation)DeltaDeno · MVTec AD downstream detectionpixel AUROC: 84.9 -> 71.4Hurt
raise last-step threshold from 0.35 to 0.60 (ablation)DeltaDeno · MVTec AD downstream detectionpixel AUROC: 84.9 -> 69.1Hurt
lower t_mid threshold from 0.6 to 0.4 (ablation)DeltaDeno · MVTec AD downstream detectionimage AUROC: 84.7 -> 86.3; AP_p 30.5 -> 35.3Mixed
zero-shot DeltaDeno vs few-shot AnoGenDeltaDeno (FLUX) · MVTec AD downstream detectionpixel AUROC: 76.7 -> 85.4Improved
zero-shot DeltaDeno vs few-shot AnomalyDiffusionDeltaDeno (FLUX) · MVTec AD downstream detectionpixel AP: 58.4 -> 41.5Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy