Instance-level object re-identification is a fundamental computer vision task, with applications from image retrieval to intelligent monitoring and fraud detection. In this work, we propose the novel task of damaged object re-identification, which aims at distinguishing changes in visual appearance due to deformations or missing parts from subtle intra-class variations. To explore this task, we leverage the power of computer-generated imagery to create, in a semi-automatic fashion, high-quality synthetic images of the same bike before and after a damage occurs. The resulting dataset, Bent & Broken Bicycles (BBBicycles), contains 39,200 images and 2,800 unique bike instances spanning 20 different bike models. As a baseline for this task, we propose TransReI3D, a multi-task, transformer-based deep network unifying damage detection (framed as a multi-label classification task) with object re-identification.

Bent & Broken Bicycles: Leveraging synthetic data for damaged object re-identification / Piano, Luca; Prattico', FILIPPO GABRIELE; Russo, ALESSANDRO SEBASTIAN; Lanari, Lorenzo; Morra, Lia; Lamberti, Fabrizio. - STAMPA. - (2023), pp. 4881-4891. ((Intervento presentato al convegno IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023 tenutosi a Waikoloa (USA) nel 03/01/2023 - 07/01/2023.

Bent & Broken Bicycles: Leveraging synthetic data for damaged object re-identification

Luca Piano;Filippo Gabriele Pratticò;Alessandro Russo;Lia Morra;Fabrizio Lamberti
2023

Abstract

Instance-level object re-identification is a fundamental computer vision task, with applications from image retrieval to intelligent monitoring and fraud detection. In this work, we propose the novel task of damaged object re-identification, which aims at distinguishing changes in visual appearance due to deformations or missing parts from subtle intra-class variations. To explore this task, we leverage the power of computer-generated imagery to create, in a semi-automatic fashion, high-quality synthetic images of the same bike before and after a damage occurs. The resulting dataset, Bent & Broken Bicycles (BBBicycles), contains 39,200 images and 2,800 unique bike instances spanning 20 different bike models. As a baseline for this task, we propose TransReI3D, a multi-task, transformer-based deep network unifying damage detection (framed as a multi-label classification task) with object re-identification.
File in questo prodotto:
File Dimensione Formato  
WACV_2023_DamagedBikes.pdf

non disponibili

Tipologia: 1. Preprint / submitted version [pre- review]
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 10.5 MB
Formato Adobe PDF
10.5 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Piano_Bent__Broken_Bicycles_Leveraging_Synthetic_Data_for_Damaged_Object_WACV_2023_paper.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 6.39 MB
Formato Adobe PDF
6.39 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2972208