AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detection

Xueyang Kang, Zizhao Li, Tian Lan, Dong Gong, Kourosh Khoshelham, Liangliang Nan

CVPR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 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 pseudo-anomaly negative augmentation during training (ablation)patch-point fusion model · Real3D-AD (object-level)AUC-ROC (%): 68.2 -> 84.2Improved
add point-to-patch cross-attention fusion (ablation)patch-point fusion model · Real3D-AD (object-level)AUC-ROC (%): 72.6 -> 84.2Improved
use RoPE cross-attention instead of vanilla cross-attention (ablation)patch-point fusion model · Real3D-AD (object-level)AUC-ROC (%): 79.1 -> 84.2Improved
add patch score modulation of normal and anomalous features (ablation)patch-point fusion model · Real3D-AD (object-level)AUC-ROC (%): 80.3 -> 84.2Improved
select the max-similarity scale instead of fusing all scales (ablation)patch codebook retrieval · Real3D-AD (object-level)AUC-ROC (%): 81.2 -> 84.2Improved
use multi-scale sphere patches instead of semantic-part patches (ablation)patchification · Real3D-AD (object-level)AUC-ROC (%): 75.1 -> 84.2Improved
use multi-scale sphere patches instead of single-scale FPS spheres (ablation)patchification · Real3D-AD (object-level)AUC-ROC (%): 81.9 -> 84.2Improved
use multi-scale spheres instead of 3D grid patches (ablation)patchification · Real3D-AD (object-level)AUC-ROC (%): 80.3 -> 84.2Improved
use mean point coordinates queried by the encoder instead of direct feature pooling for patch features (ablation)patch feature extraction · Real3D-AD (object-level)AUC-ROC (%): 77.8 -> 79.4Improved
increase patch size beyond 64 (ablation)patchification · Real3D-ADAUC-ROCHurt
increase voxel resolution beyond 128^3 (ablation)preprocessing · Real3D-ADAUC-ROCNo clear effect
increase patch number beyond 128 (ablation)patchification · Real3D-ADAUC-ROCNo clear effect

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