Replacing Real Faces with Virtual Humans: A New Paradigm for Facial De-Identification

• Paulo Knob PUCRS / INCT-SANI
• Erick Menezes UNIT / INCT-SANI
• Rafael Mecenas UNIT
• Gabriel Ferri Schneider PUCRS
• Ana Carolina Xavier PUCRS
• Victor Araujo UNIT / INCT-SANI
• Soraia Musse PUCRS

Resumo

Face de-identification seeks to protect individual privacy in visual data while preserving useful facial features. In this work, we propose a novel approach that replaces original facial images with realistic 3D virtual human representations. These persistent virtual faces, generated via automatic reconstruction (Deep3D) and manual tailoring (MetaHumans), serve as identity representatives, enabling face recognition without storing real biometric data. We created multiple datasets of virtual faces based on two public datasets (CFD and MEAD), while also applying transformations on a few selected virtual faces, such as age progression, skin tone variation, and emotional expression changes. Our experiments, using Adam’s face recognition algorithm, show that even modified virtual faces consistently match their real counterparts with high accuracy.

Referências

T. Orekondy, M. Fritz, and B. Schiele, “Connecting pixels to privacy and utility: Automatic redaction of private information in images,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8466–8475.

K. Brkic, I. Sikiric, T. Hrkac, and Z. Kalafatic, “I know that person: Generative full body and face de-identification of people in images,” in 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW). IEEE, 2017, pp. 1319–1328.

R. Hasan, P. Shaffer, D. Crandall, E. T. Apu Kapadia et al., “Cartooning for enhanced privacy in lifelogging and streaming videos,” in Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 2017, pp. 29–38.

Y. Zhang, Y. Fang, Y. Cao, and J. Wu, “Rbgan: Realistic-generation and balanced-utility gan for face de-identification,” Image and Vision Computing, vol. 141, p. 104868, 2024.

E. M. Newton, L. Sweeney, and B. Malin, “Preserving privacy by deidentifying face images,” IEEE transactions on Knowledge and Data Engineering, vol. 17, no. 2, pp. 232–243, 2005.

S. Ravi, P. Climent-Pérez, and F. Florez-Revuelta, “A review on visual privacy preservation techniques for active and assisted living,” Multimedia Tools and Applications, vol. 83, no. 5, pp. 14 715–14 755, 2024.

R. Zhao, Y. Zhang, T. Wang, W. Wen, Y. Xiang, and X. Cao, “Visual content privacy protection: A survey,” ACM Computing Surveys, vol. 57, no. 5, pp. 1–36, 2025.

B. Jiang, B. Bai, H. Lin, Y. Wang, Y. Guo, and L. Fang, “Dartblur: Privacy preservation with detection artifact suppression,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 16 479–16 488.

J. Lopez, C. Hinojosa, H. Arguello, and B. Ghanem, “Privacy-preserving optics for enhancing protection in face de-identification,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 12 120–12 129.

S. Barattin, C. Tzelepis, I. Patras, and N. Sebe, “Attribute-preserving face dataset anonymization via latent code optimization,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023, pp. 8001–8010.

J. Cao, B. Liu, Y. Wen, R. Xie, and L. Song, “Personalized and invertible face de-identification by disentangled identity information manipulation,” in Proceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 3334–3342.

R. More, A. Maity, G. Kambli, and S. Ambadekar, “Privacy-preserving video analytics through gan-based face de-identification,” in 2024 Second International Conference on Networks, Multimedia and Information Technology (NMITCON). IEEE, 2024, pp. 1–6.

D. S. Ma, J. Correll, and B. Wittenbrink, “The chicago face database: A free stimulus set of faces and norming data,” Behavior research methods, vol. 47, pp. 1122–1135, 2015.

D. S. Ma, J. Kantner, and B. Wittenbrink, “Chicago face database: Multiracial expansion,” Behavior Research Methods, vol. 53, pp. 1289–1300, 2021.

A. Lakshmi, B. Wittenbrink, J. Correll, and D. S. Ma, “The india face set: International and cultural boundaries impact face impressions and perceptions of category membership,” Frontiers in psychology, vol. 12, p. 627678, 2021.

K. Wang, Q. Wu, L. Song, Z. Yang, W. Wu, C. Qian, R. He, Y. Qiao, and C. C. Loy, “Mead: A large-scale audio-visual dataset for emotional talking-face generation,” in ECCV, 2020.

Y. Deng, J. Yang, S. Xu, D. Chen, Y. Jia, and X. Tong, “Accurate 3d face reconstruction with weakly-supervised learning: From single image to image set,” in IEEE Computer Vision and Pattern Recognition Workshops, 2019.

C. Schumann, G. O. Olanubi, A. Wright, E. Monk Jr, C. Heldreth, and S. Ricco, “Consensus and subjectivity of skin tone annotation for ml fairness,” arXiv preprint arXiv:2305.09073, 2023.

C. Li, K. Zhou, and S. Lin, “Intrinsic face image decomposition with human face priors,” in Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 2014, pp. 218–233.

P. Ekman, “An argument for basic emotions,” Cognition & emotion, vol. 6, no. 3-4, pp. 169–200, 1992.

Z. Zhang, Y. Song, and H. Qi, “Age progression/regression by conditional adversarial autoencoder,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2017, pp. 4352–4360.

N. Kumar, A. C. Berg, P. N. Belhumeur, and S. K. Nayar, “Attribute and simile classifiers for face verification,” in 2009 IEEE 12th International Conference on Computer Vision. IEEE, 2009, pp. 365–372.

Z. Liu, P. Luo, X. Wang, and X. Tang, “Deep learning face attributes in the wild,” in Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 3730–3738.