Selected work

Representative Papers

VT-3DAD: Cross-Category 3D Anomaly Detection via Visual-Text Normal Space Alignment

Jun 02, 2026

This work addresses the challenge of cross-category 3D point cloud anomaly detection using only a few normal samples by proposing a training-free framework that, for the first time, introduces vision–text normal space alignment to this task. The method extracts visual features from multi-view depth maps using a frozen CLIP model and constructs semantic normal anchors via depth-aware and 3D-aware textual prompts. Anomaly scores are computed by fusing visual and semantic deviations. Evaluated on ShapeNetPart, the approach achieves an average single-sample AUC-ROC of 94.80%, outperforming a purely visual baseline by 2.31% and reducing the standard deviation from 5.64 to 3.41. These results demonstrate the effectiveness of the proposed method in jointly modeling geometric and semantic normality, as well as its strong cross-category generalization capability.

0 citationsRead paper

DMP-3DAD: Cross-Category 3D Anomaly Detection via Realistic Depth Map Projection with Few Normal Samples

Feb 11, 2026

This work addresses the challenge of cross-category 3D point cloud anomaly detection using only a few normal samples by proposing the first training-free, general-purpose framework. The method projects 3D point clouds into multi-view realistic depth maps and leverages a frozen CLIP vision encoder to extract features, enabling anomaly identification through weighted feature similarity without any category-specific fine-tuning or adaptation. Experimental results demonstrate that the approach achieves state-of-the-art performance under few-shot settings on the ShapeNetPart dataset, significantly enhancing the generality, practicality, and robustness of cross-category 3D anomaly detection.

0 citationsRead paper

Efficient Enumeration of At Most $k$-Out Polygons

Sep 16, 2025

This paper addresses the efficient enumeration of all simple polygons—termed *k-outer polygons*—whose vertices are drawn from a set $S$ of $n$ points in general position (no three collinear) in the Euclidean plane and that contain at most $k$ points of $S$ in their exterior. We propose a novel output-sensitive algorithm based on convex hull layering and polar-angle-ordered scanning, which dynamically maintains visibility structures and eliminates duplicate polygon generation. Our method achieves an enumeration delay of $mathcal{O}(n^2 log n)$, improving upon the previous best bound of $mathcal{O}(n^3 log n)$; it is the first algorithm to attain this delay complexity. Theoretical analysis confirms asymptotic optimality with respect to delay, and empirical evaluation demonstrates scalability on large point sets. The approach is applicable to geometric shape analysis, boundary pattern mining, and related computational geometry tasks.

0 citationsRead paper

3DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clustering

Jul 17, 2025

To address the challenges of high computational cost, sensitivity to spatial misalignment, and difficulty in modeling local structural discrepancies in fine-grained anomaly detection for high-resolution 3D point clouds, this paper proposes a keypoint-guided clustering and multi-prototype alignment framework. Methodologically, it first identifies robust clustering centers via geometric saliency-driven keypoint detection; then achieves cross-sample local region alignment through point cloud registration and enhances anomaly sensitivity via multi-prototype feature representation; finally performs fine-grained feature discrepancy analysis at the cluster level for precise anomaly localization. The method operates solely on raw point cloud features, requiring no additional supervision or reconstruction modules. On the Real3D-AD benchmark, it achieves state-of-the-art performance in both object-level and point-level anomaly detection, demonstrating superior efficiency and robustness.

0 citationsRead paper

Recent publications

Latest Papers

VT-3DAD: Cross-Category 3D Anomaly Detection via Visual-Text Normal Space Alignment

Jun 02, 2026

This work addresses the challenge of cross-category 3D point cloud anomaly detection using only a few normal samples by proposing a training-free framework that, for the first time, introduces vision–text normal space alignment to this task. The method extracts visual features from multi-view depth maps using a frozen CLIP model and constructs semantic normal anchors via depth-aware and 3D-aware textual prompts. Anomaly scores are computed by fusing visual and semantic deviations. Evaluated on ShapeNetPart, the approach achieves an average single-sample AUC-ROC of 94.80%, outperforming a purely visual baseline by 2.31% and reducing the standard deviation from 5.64 to 3.41. These results demonstrate the effectiveness of the proposed method in jointly modeling geometric and semantic normality, as well as its strong cross-category generalization capability.

0 citationsRead paper

DMP-3DAD: Cross-Category 3D Anomaly Detection via Realistic Depth Map Projection with Few Normal Samples

Feb 11, 2026

This work addresses the challenge of cross-category 3D point cloud anomaly detection using only a few normal samples by proposing the first training-free, general-purpose framework. The method projects 3D point clouds into multi-view realistic depth maps and leverages a frozen CLIP vision encoder to extract features, enabling anomaly identification through weighted feature similarity without any category-specific fine-tuning or adaptation. Experimental results demonstrate that the approach achieves state-of-the-art performance under few-shot settings on the ShapeNetPart dataset, significantly enhancing the generality, practicality, and robustness of cross-category 3D anomaly detection.

0 citationsRead paper

Efficient Enumeration of At Most $k$-Out Polygons

Sep 16, 2025

This paper addresses the efficient enumeration of all simple polygons—termed *k-outer polygons*—whose vertices are drawn from a set $S$ of $n$ points in general position (no three collinear) in the Euclidean plane and that contain at most $k$ points of $S$ in their exterior. We propose a novel output-sensitive algorithm based on convex hull layering and polar-angle-ordered scanning, which dynamically maintains visibility structures and eliminates duplicate polygon generation. Our method achieves an enumeration delay of $mathcal{O}(n^2 log n)$, improving upon the previous best bound of $mathcal{O}(n^3 log n)$; it is the first algorithm to attain this delay complexity. Theoretical analysis confirms asymptotic optimality with respect to delay, and empirical evaluation demonstrates scalability on large point sets. The approach is applicable to geometric shape analysis, boundary pattern mining, and related computational geometry tasks.

0 citationsRead paper

3DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clustering

Jul 17, 2025

To address the challenges of high computational cost, sensitivity to spatial misalignment, and difficulty in modeling local structural discrepancies in fine-grained anomaly detection for high-resolution 3D point clouds, this paper proposes a keypoint-guided clustering and multi-prototype alignment framework. Methodologically, it first identifies robust clustering centers via geometric saliency-driven keypoint detection; then achieves cross-sample local region alignment through point cloud registration and enhances anomaly sensitivity via multi-prototype feature representation; finally performs fine-grained feature discrepancy analysis at the cluster level for precise anomaly localization. The method operates solely on raw point cloud features, requiring no additional supervision or reconstruction modules. On the Real3D-AD benchmark, it achieves state-of-the-art performance in both object-level and point-level anomaly detection, demonstrating superior efficiency and robustness.

0 citationsRead paper