Looking 3D: Anomaly detection with 2D-3D alignment

Ankan Bhunia, Changjian Li, Hakan Bilen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Number of pages10
Publication statusAccepted/In press - 6 Mar 2024
EventThe IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024 - Seattle, United States
Duration: 17 Jun 202421 Jun 2024


ConferenceThe IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024
Abbreviated titleCVPR 2024
Country/TerritoryUnited States
Internet address


Dive into the research topics of 'Looking 3D: Anomaly detection with 2D-3D alignment'. Together they form a unique fingerprint.

Cite this