Nowadays, deep learning models have reached incredible performance in the task of image generation. Plenty of literature works address the task of face generation and editing, with human and automatic systems that struggle to distinguish what's real from generated. Whereas most systems reached excellent visual generation quality, they still face difficulties in preserving the identity of the starting input subject. Among all the explored techniques, Semantic Image Synthesis (SIS) methods, whose goal is to generate an image conditioned on a semantic segmentation mask, are the most promising, even though preserving the perceived identity of the input subject is not their main concern. Therefore, in this paper, we investigate the problem of identity preservation in face image generation and present an SIS architecture that exploits a cross-attention mechanism to merge identity, style, and semantic features to generate faces whose identities are as similar as possible to the input ones. Experimental results reveal that the proposed method is not only suitable for preserving the identity but is also effective in the face recognition adversarial attack, i.e. hiding a second identity in the generated faces.

Adversarial Identity Injection for Semantic Face Image Synthesis / Tarollo, G.; Fontanini, T.; Ferrari, C.; Borghi, G.; Prati, A.. - (2024), pp. 1471-1480. (Intervento presentato al convegno 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024 tenutosi a usa nel 2024) [10.1109/CVPRW63382.2024.00154].

Adversarial Identity Injection for Semantic Face Image Synthesis

Borghi G.;
2024

Abstract

Nowadays, deep learning models have reached incredible performance in the task of image generation. Plenty of literature works address the task of face generation and editing, with human and automatic systems that struggle to distinguish what's real from generated. Whereas most systems reached excellent visual generation quality, they still face difficulties in preserving the identity of the starting input subject. Among all the explored techniques, Semantic Image Synthesis (SIS) methods, whose goal is to generate an image conditioned on a semantic segmentation mask, are the most promising, even though preserving the perceived identity of the input subject is not their main concern. Therefore, in this paper, we investigate the problem of identity preservation in face image generation and present an SIS architecture that exploits a cross-attention mechanism to merge identity, style, and semantic features to generate faces whose identities are as similar as possible to the input ones. Experimental results reveal that the proposed method is not only suitable for preserving the identity but is also effective in the face recognition adversarial attack, i.e. hiding a second identity in the generated faces.
2024
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024
usa
2024
1471
1480
Tarollo, G.; Fontanini, T.; Ferrari, C.; Borghi, G.; Prati, A.
Adversarial Identity Injection for Semantic Face Image Synthesis / Tarollo, G.; Fontanini, T.; Ferrari, C.; Borghi, G.; Prati, A.. - (2024), pp. 1471-1480. (Intervento presentato al convegno 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024 tenutosi a usa nel 2024) [10.1109/CVPRW63382.2024.00154].
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1367127
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact