AI Paper Atlas

Research map / Point clouds / Point cloud classification

R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection

Zheyuan Zhou, Le Wang, Naiyu Fang, Zili Wang, Lemiao Qiu, Shuyou Zhang

ECCV 2024 · Point clouds › Point cloud classification · approach: Point cloud detection and tracking · 44 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 shape embedding condition to vanilla DDPM (ablation)R3D-AD · Real3D-ADI-AUROC: 0.586 -> 0.667Improved
add latent shape embedding condition to vanilla DDPM (ablation)R3D-AD · Real3D-ADP-AUROC: 0.524 -> 0.513No clear effect
predict relative point displacements instead of absolute shape (ablation)R3D-AD · Real3D-ADP-AUROC: 0.513 -> 0.573Improved
predict relative point displacements instead of absolute shape (ablation)R3D-AD · Real3D-ADI-AUROC: 0.667 -> 0.712Improved
add Patch-Gen anomaly simulation (ablation)R3D-AD · Real3D-ADI-AUROC: 0.712 -> 0.734Improved
Patch-Gen selection ratio raised from 1/32 to 1/8 (ablation)Patch-Gen · Real3D-ADI-AUROC: 0.734 -> 0.683Hurt
Patch-Gen selection ratio lowered from 1/32 to 1/64 (ablation)Patch-Gen · Real3D-ADI-AUROC: 0.734 -> 0.716Hurt
increase Patch-Gen scaling factor from 0.1 to 0.8 (ablation)Patch-Gen · Real3D-ADI-AUROC: 0.734 -> 0.661Hurt
replace memory-bank/embedding methods with one-step diffusion reconstruction on raw points3D anomaly detection · Anomaly-ShapeNetI-AUROC (average): 0.659 -> 0.749Improved
replace memory-bank/embedding methods with one-step diffusion reconstruction on raw points3D anomaly detection · Real3D-ADI-AUROC (average): 0.725 -> 0.734Improved
train on a subset of bowl categories and test on unseen bowl4R3D-AD · Anomaly-ShapeNetI-AUROC: 0.744 -> 0.715Mixed
train on ShapeNetCore.v2 and test on Real3D-AD (cross-dataset)R3D-AD · Real3D-AD AirplaneI-AUROC: 0.772 -> 0.614Hurt

Later papers that compared with this method

4 later accepted papers report R3D-AD as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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