AI Paper Atlas

Research map / Point clouds / Point cloud classification

Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detection

Ali Balapour, Faraz Hach

ECCV 2026 · Point clouds › Point cloud classification · approach: Point cloud detection and tracking · 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
replace Norm-AS with AF3AD synthesis in PO3ADPO3AD · AnomalyShapeNetO-AUROC: 83.9 -> 91.5Improved
replace Norm-AS with AF3AD synthesis in PO3ADPO3AD · Real3D-ADO-AUROC: 76.6 -> 85.2Improved
replace Patch-Gen with AF3AD in R3D-ADR3D-AD · AnomalyShapeNet (15 classes)O-AUROC: 62.7 -> 67.2Improved
R3D-AD with AF3AD versus released R3D-AD without Patch-GenR3D-AD · AnomalyShapeNet (15 classes)O-AUROC: 58.7 -> 67.2Improved
replace Patch-Gen with AF3AD in R3D-ADR3D-AD · AnomalyShapeNet (15 classes)P-AUROC: 60.7 -> 60.7No clear effect
add multi-head offset prediction to AF3AD training (ablation)PO3AD+AF3AD · AnomalyShapeNet (15 classes, h=128)O-AUROC: 90.3 -> 97.0Improved
AF3AD instead of Norm-AS synthesis under multi-head h=128 (ablation)PO3AD multi-head · AnomalyShapeNet (15 classes)O-AUROC: 91.6 -> 97.0Improved
AF3AD instead of Norm-AS with weak baseline head h=32 (ablation)PO3AD baseline head · AnomalyShapeNet (15 classes, h=32)O-AUROC: 90.9 -> 88.4Hurt
combine preset groups A, B, C, D versus group A alone (ablation)AF3AD · AnomalyShapeNet (15 classes, index-0 split)O-AUROC: 62.5 -> 88.9Improved
add groups A, C, D to best single group B (ablation)AF3AD · AnomalyShapeNet (15 classes, index-0 split)O-AUROC: 74.0 -> 88.9Improved
add Gaussian noise sigma 0.001 to test data (ablation)AF3AD · AnomalyShapeNet (15 classes)O-AUROC: 93.3 -> 93.3No clear effect
add Gaussian noise sigma 0.003 to test data (ablation)AF3AD · AnomalyShapeNet (15 classes)P-AUPR: 59.0 -> 29.6Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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