AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Geometry-Aligned and Anomaly-Aware Reconstruction for 3D Anomaly Detection

Linchun Wu, Qin Zou, Yuanhao Yue, Zhongyuan Wang

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Reconstruction-based diffusion image detection

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 geometry noise rectification (ablation)AARD baseline · Anomaly-ShapeNetO-AUROC: 0.772 -> 0.802Improved
add vertex noise rectification (ablation)AARD baseline · Anomaly-ShapeNetO-AUROC: 0.772 -> 0.796Improved
combine geometry and vertex noise rectification (ablation)AARD baseline · Anomaly-ShapeNetF-Score: 0.719 -> 0.832Improved
add normal reference and anomaly mask on top of noise rectification (ablation)AARD · Anomaly-ShapeNetO-AUROC: 0.825 -> 0.915Improved
add input reference and anomaly mask on top of noise rectification (ablation)AARD · Anomaly-ShapeNetO-AUROC: 0.825 -> 0.893Improved
add input reference to normal reference and mask (full model) (ablation)AARD · Anomaly-ShapeNetO-AUROC: 0.915 -> 0.931Improved
add normal reference to input reference and mask (ablation)AARD · Anomaly-ShapeNetF-Score: 0.947 -> 0.953No clear effect
add NR, IR and AM to noise rectification (ablation)AARD · Anomaly-ShapeNetF-Score: 0.832 -> 0.953Improved
vary grid number g from 4 to 2 or 10 (ablation)geometry rectification · Anomaly-ShapeNetO-AUROC: 0.931 -> 0.857 (g=2); 0.931 -> 0.898 (g=10)Hurt
vary vertex group size k from 16 to 8 or 40 (ablation)vertex rectification · Anomaly-ShapeNetO-AUROC: 0.931 -> 0.891 (k=8); 0.931 -> 0.886 (k=40)Hurt
vary gamma from 0.5 to 0.1 or 0.9 (ablation)vertex rectification · Anomaly-ShapeNetO-AUROC: 0.931 -> 0.889 (0.1); 0.931 -> 0.908 (0.9)Hurt
AARD versus PASDF on Car and Fish categoriesAARD · Real3D-ADO-AUROC: Car 0.725 vs 0.959; Fish 0.891 vs 0.989 (PASDF)Mixed

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