In this paper, we propose a technique to detect and localize inpainting created by diffusion-based machine learning models. We begin by compiling a dataset of inpainted images, which we then use to train a convolutional neural network (CNN) for this task. Our method achieves high precision, recall, F1-score, and Intersection over Union (IoU) in detecting and localizing inpainting. It is versatile and can be applied to various real-life scenarios.
InpaintLocalizer: Detection and Localization of Inpainting Generated by Diffusion-Based Machine Learning Models / De Magistris, G.; Pinto, M. L.; Najgebauer, P.; Scherer, R.; Napoli, C.. - 15165:(2025), pp. 245-257. ( 23rd International Conference on Artificial Intelligence and Soft Computing, ICAISC 2024 Zakopane; pol ) [10.1007/978-3-031-84356-3_20].
InpaintLocalizer: Detection and Localization of Inpainting Generated by Diffusion-Based Machine Learning Models
Napoli C.
Ultimo
Supervision
2025
Abstract
In this paper, we propose a technique to detect and localize inpainting created by diffusion-based machine learning models. We begin by compiling a dataset of inpainted images, which we then use to train a convolutional neural network (CNN) for this task. Our method achieves high precision, recall, F1-score, and Intersection over Union (IoU) in detecting and localizing inpainting. It is versatile and can be applied to various real-life scenarios.| File | Dimensione | Formato | |
|---|---|---|---|
|
DeMagistris_InpaintLocalizer_2025.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
2.93 MB
Formato
Adobe PDF
|
2.93 MB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
