7 papers
Learning Discriminative Signed Distance Functions from Multi-scale Level-of-detail Features for 3D Anomaly Detection
Haibo Xiao, Hanzhe Liang, Jie Zhou +2
Detecting anomalies from 3D point clouds has received increasing attention in the field of computer vision, with some group-based or point-based methods achieving impressive result…
Identity-Consistent Multi-Pose Generation of Contactless Fingerprints
Zhiyu Pan, Xiongjun Guan, Jianjiang Feng +1
Contactless fingerprint recognition has gained increasing attention due to its advantages in hygiene and acquisition flexibility. However, the absence of physical contact constrain…
A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Features
Hanzhe Liang, Jie Zhou, Can Gao +3
3D anomaly detection (AD) is a crucial task in computer vision, aiming to identify anomalous points or regions from point cloud data. However, existing methods may encounter challe…
Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detection
Hanzhe Liang, Aoran Wang, Jie Zhou +3
In this paper, we explore a novel approach to 3D anomaly detection (AD) that goes beyond merely identifying anomalies based on structural characteristics. Our primary perspective i…
Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detection
Hanzhe Liang, Jie Zhou, Xuanxin Chen +3
3D anomaly detection (AD) is prominent but difficult due to lacking a unified theoretical foundation for preprocessing design. We establish the Fence Theorem, formalizing preproces…
Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space
Linchao Pan, Can Gao, Jie Zhou +1
Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from know…