PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Qihang, Yan, Jiangtao, He, Shibo, Meng, Wenchao, Chen, Jiming
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929643092705280
author Zhou, Qihang
Yan, Jiangtao
He, Shibo
Meng, Wenchao
Chen, Jiming
author_facet Zhou, Qihang
Yan, Jiangtao
He, Shibo
Meng, Wenchao
Chen, Jiming
contents Zero-shot (ZS) 3D anomaly detection is a crucial yet unexplored field that addresses scenarios where target 3D training samples are unavailable due to practical concerns like privacy protection. This paper introduces PointAD, a novel approach that transfers the strong generalization capabilities of CLIP for recognizing 3D anomalies on unseen objects. PointAD provides a unified framework to comprehend 3D anomalies from both points and pixels. In this framework, PointAD renders 3D anomalies into multiple 2D renderings and projects them back into 3D space. To capture the generic anomaly semantics into PointAD, we propose hybrid representation learning that optimizes the learnable text prompts from 3D and 2D through auxiliary point clouds. The collaboration optimization between point and pixel representations jointly facilitates our model to grasp underlying 3D anomaly patterns, contributing to detecting and segmenting anomalies of unseen diverse 3D objects. Through the alignment of 3D and 2D space, our model can directly integrate RGB information, further enhancing the understanding of 3D anomalies in a plug-and-play manner. Extensive experiments show the superiority of PointAD in ZS 3D anomaly detection across diverse unseen objects.
format Preprint
id arxiv_https___arxiv_org_abs_2410_00320
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection
Zhou, Qihang
Yan, Jiangtao
He, Shibo
Meng, Wenchao
Chen, Jiming
Computer Vision and Pattern Recognition
Computation and Language
Zero-shot (ZS) 3D anomaly detection is a crucial yet unexplored field that addresses scenarios where target 3D training samples are unavailable due to practical concerns like privacy protection. This paper introduces PointAD, a novel approach that transfers the strong generalization capabilities of CLIP for recognizing 3D anomalies on unseen objects. PointAD provides a unified framework to comprehend 3D anomalies from both points and pixels. In this framework, PointAD renders 3D anomalies into multiple 2D renderings and projects them back into 3D space. To capture the generic anomaly semantics into PointAD, we propose hybrid representation learning that optimizes the learnable text prompts from 3D and 2D through auxiliary point clouds. The collaboration optimization between point and pixel representations jointly facilitates our model to grasp underlying 3D anomaly patterns, contributing to detecting and segmenting anomalies of unseen diverse 3D objects. Through the alignment of 3D and 2D space, our model can directly integrate RGB information, further enhancing the understanding of 3D anomalies in a plug-and-play manner. Extensive experiments show the superiority of PointAD in ZS 3D anomaly detection across diverse unseen objects.
title PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2410.00320