Salvato in:
Dettagli Bibliografici
Autori principali: Bhunia, Ankan, Li, Changjian, Bilen, Hakan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2406.19393
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917707676385280
author Bhunia, Ankan
Li, Changjian
Bilen, Hakan
author_facet Bhunia, Ankan
Li, Changjian
Bilen, Hakan
contents Automatic anomaly detection based on visual cues holds practical significance in various domains, such as manufacturing and product quality assessment. This paper introduces a new conditional anomaly detection problem, which involves identifying anomalies in a query image by comparing it to a reference shape. To address this challenge, we have created a large dataset, BrokenChairs-180K, consisting of around 180K images, with diverse anomalies, geometries, and textures paired with 8,143 reference 3D shapes. To tackle this task, we have proposed a novel transformer-based approach that explicitly learns the correspondence between the query image and reference 3D shape via feature alignment and leverages a customized attention mechanism for anomaly detection. Our approach has been rigorously evaluated through comprehensive experiments, serving as a benchmark for future research in this domain.
format Preprint
id arxiv_https___arxiv_org_abs_2406_19393
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Looking 3D: Anomaly Detection with 2D-3D Alignment
Bhunia, Ankan
Li, Changjian
Bilen, Hakan
Computer Vision and Pattern Recognition
Automatic anomaly detection based on visual cues holds practical significance in various domains, such as manufacturing and product quality assessment. This paper introduces a new conditional anomaly detection problem, which involves identifying anomalies in a query image by comparing it to a reference shape. To address this challenge, we have created a large dataset, BrokenChairs-180K, consisting of around 180K images, with diverse anomalies, geometries, and textures paired with 8,143 reference 3D shapes. To tackle this task, we have proposed a novel transformer-based approach that explicitly learns the correspondence between the query image and reference 3D shape via feature alignment and leverages a customized attention mechanism for anomaly detection. Our approach has been rigorously evaluated through comprehensive experiments, serving as a benchmark for future research in this domain.
title Looking 3D: Anomaly Detection with 2D-3D Alignment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.19393