Current face anonymization techniques often depend on identity loss calculated by face recognition models, which can be inaccurate and unreliable. Additionally, many methods require supplementary data such as facial landmarks and masks to guide the synthesis process. In contrast, our approach uses diffusion models with only a reconstruction loss, eliminating the need for facial landmarks or masks while still producing images with intricate, fine-grained details. We validated our results on two public benchmarks through both quantitative and qualitative evaluations. Our model achieves state-of-the-art performance in three key areas: identity anonymization, facial attribute preservation, and image quality. Beyond its primary function of anonymization, our model can also perform face swapping tasks by incorporating an additional facial image as input, demonstrating its versatility and potential for diverse applications. Our code and models are available at https://github.com/hanweikung/face_anon_simple.

Face Anonymization Made Simple / Kung, Han-Wei; Varanka, Tuomas; Saha, Sanjay; Sim, Terence; Sebe, Nicu. - (2025), pp. 1040-1050. (Intervento presentato al convegno 2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025 tenutosi a usa nel 2025) [10.1109/WACV61041.2025.00110].

Face Anonymization Made Simple

Kung, Han-Wei;Sebe, Nicu
2025-01-01

Abstract

Current face anonymization techniques often depend on identity loss calculated by face recognition models, which can be inaccurate and unreliable. Additionally, many methods require supplementary data such as facial landmarks and masks to guide the synthesis process. In contrast, our approach uses diffusion models with only a reconstruction loss, eliminating the need for facial landmarks or masks while still producing images with intricate, fine-grained details. We validated our results on two public benchmarks through both quantitative and qualitative evaluations. Our model achieves state-of-the-art performance in three key areas: identity anonymization, facial attribute preservation, and image quality. Beyond its primary function of anonymization, our model can also perform face swapping tasks by incorporating an additional facial image as input, demonstrating its versatility and potential for diverse applications. Our code and models are available at https://github.com/hanweikung/face_anon_simple.
2025
2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
New York
Institute of Electrical and Electronics Engineers Inc.
9798331510831
Kung, Han-Wei; Varanka, Tuomas; Saha, Sanjay; Sim, Terence; Sebe, Nicu
Face Anonymization Made Simple / Kung, Han-Wei; Varanka, Tuomas; Saha, Sanjay; Sim, Terence; Sebe, Nicu. - (2025), pp. 1040-1050. (Intervento presentato al convegno 2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025 tenutosi a usa nel 2025) [10.1109/WACV61041.2025.00110].
File in questo prodotto:
File Dimensione Formato  
Kung_Face_Anonymization_Made_Simple_WACV_2025_paper.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 3.77 MB
Formato Adobe PDF
3.77 MB Adobe PDF Visualizza/Apri
Face_Anonymization_Made_Simple.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 3.69 MB
Formato Adobe PDF
3.69 MB Adobe PDF   Visualizza/Apri

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/11572/453795
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact