Abstract
The increasing prevalence of computer vision applications in public spaces has raised substantial privacy concerns regarding facial image data. Traditional anonymization methods, despite their potential, often suffer from drawbacks such as limited output variety, inadequate detail, distortions in extreme poses, and inconsistent temporal patterns. This study introduces an identity diffuser based on a dual-conditional diffusion model that efficiently anonymizes facial images while preserving task-relevant features for diverse applications. Our approach ensures a clear separation from the original identity by utilizing synthetic identities and an optimized identity feature space derived from three state-of-the-art models. It maintains consistency across frames for video anonymization. Unlike existing methods, our approach eliminates the need for task-relevant feature extractors, such as those for pose and expression. Instead, it employs a dual-condition diffusion model to integrate both identity and non-identity information, offering improved anonymization without compromising data usefulness. Our technique enables seamless transitions from real to synthetic identities by incorporating a time-step-dependent ID loss, providing controllable identity anonymization. Extensive studies demonstrate that our method achieves superior de-identification rates and consistency compared to state-of-the-art techniques, preserving non-identity features with a 20% improvement in emotion recognition, handling extreme poses with enhanced image quality, output diversity, and temporal consistency. This makes it a valuable tool for privacy-preserving computer vision applications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
For fair analysis and due to the unavailability of released code, we borrowed qualitative and quantitative results from [5] for comparison in our work. This ensures fair and consistent analysis, as altering the input images could impact the results.
References
Legal text. general data protection regulation (gdpr). (2024, april 22). https://gdpr-info.eu/
Barattin, S., Tzelepis, C., Patras, I., Sebe, N.: Attribute-preserving face dataset anonymization via latent code optimization pp. 8001–8010
Boutros, F., Huber, M., Siebke, P., Rieber, T., Damer, N.: Sface: Privacy-friendly and accurate face recognition using synthetic data. In: 2022 IEEE International Joint Conference on Biometrics (IJCB). pp. 1–11. IEEE (2022)
Bu, J., Jiang, R.L., Zheng, B.: Research on deepfake technology and its application. In: International Conference on Computing, Networks and Internet of Things (CNIOT). pp. 47–51 (2023)
Cai, Z., Gao, Z., Planche, B., Zheng, M., Chen, T., Asif, M.S., Wu, Z.: Disguise without disruption: Utility-preserving face de-identification. Conference on Artificial Intelligence (AAAI) p. 918-926 (2024)
Canada, G.: The personal information protection and electronic documents act (2021), https://www.priv.gc.ca/en/privacy-topics/privacy-laws-in-canada/the-personal-information-protection-and-electronic-documents-act-pipeda/
Cao, J., Liu, B., Wen, Y., Xie, R., Song, L.: Personalized and invertible face de-identification by disentangled identity information manipulation pp. 3334–3342
Chen, R., Chen, X., Ni, B., Ge, Y.: Simswap: An efficient framework for high fidelity face swapping. In: International Conference on Multimedia (ACMMM). pp. 2003–2011 (2020)
Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: Additive angular margin loss for deep face recognition. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 4690–4699 (2019)
Gafni, O., Wolf, L., Taigman, Y.: Live face de-identification in video. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 9378–9387 (2019)
Gu, X., Luo, W., Ryoo, M.S., Lee, Y.J.: Password-Conditioned Anonymization and Deanonymization with Face Identity Transformers, p. 727-743 (2020)
He, X., Zhu, M., Chen, D., Wang, N., Gao, X.: Diff-privacy: Diffusion-based face privacy protection (2023)
Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems (NIPS), volume=33, pages=6840–6851, year=2020
Huang, G., Mattar, M., Lee, H., Learned-Miller, E.: Learning to align from scratch. Advances in Neural Information Processing Systems (NIPS), volume=25, year=2012
Huang, G.B., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: A database forstudying face recognition in unconstrained environments. In: Workshop on faces in’Real-Life’Images: detection, alignment, and recognition (2008)
Hukkelås, H., Lindseth, F.: Deepprivacy2: Towards realistic full-body anonymization pp. 1329–1338 (2020)
Hukkelås, H., Mester, R., Lindseth, F.: DeepPrivacy: A Generative Adversarial Network for Face Anonymization, p. 565-578. Springer International Publishing (2019)
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 4401–4410 (2019)
Kim, M., Jain, A.K., Liu, X.: Adaface: Quality adaptive margin for face recognition. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 18750–18759 (2022)
Kim, M., Liu, F., Jain, A., Liu, X.: Dcface: Synthetic face generation with dual condition diffusion model. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 12715–12725 (2023)
Kuang, Z., Yang, X., Shen, Y., Hu, C., Yu, J.: Facial identity anonymization via intrinsic and extrinsic attention distraction. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 12406–12415 (2024)
Laishram, L., Shaheryar, M., Lee, J.T., Jung, S.K.: Toward a privacy-preserving face recognition system: A survey of leakages and solutions. ACM Computing Surveys (2024)
Li, J., Han, L., Chen, R., Zhang, H., Han, B., Wang, L., Cao, X.: Identity-preserving face anonymization via adaptively facial attributes obfuscation. In: International Conference on Multimedia (ACMMM). pp. 3891–3899 (2021)
Li, L., Bao, J., Yang, H., Chen, D., Wen, F.: Advancing high fidelity identity swapping for forgery detection. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 5074–5083 (2020)
Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: Sphereface: Deep hypersphere embedding for face recognition. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 212–220 (2017)
Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van Gool, L.: Repaint: Inpainting using denoising diffusion probabilistic models. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 11461–11471 (2022)
Maximov, M., Elezi, I., Leal-Taixé, L.: Ciagan: Conditional identity anonymization generative adversarial networks. pp. 5447–5456 (2020)
Maximov, M., Elezi, I., Leal-Taixé, L.: Decoupling identity and visual quality for image and video anonymization. In: Asian Conference on Computer Vision (ACCV). pp. 3637–3653 (2022)
McPherson, R., Shokri, R., Shmatikov, V.: Defeating image obfuscation with deep learning. arXiv preprint arXiv:1609.00408 (2016)
Neustaedter, C., Greenberg, S., Boyle, M.: Blur filtration fails to preserve privacy for home-based video conferencing. ACM Transactions on Computer-Human Interaction 13(1), 1–36 (2006)
Newton, E.M., Sweeney, L., Malin, B.: Preserving privacy by de-identifying face images. IEEE Trans. Knowl. Data Eng. 17(2), 232–243 (2005)
Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. pp. 8162–8171. PMLR (2021)
Qiu, H., Yu, B., Gong, D., Li, Z., Liu, W., Tao, D.: Synface: Face recognition with synthetic data. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 10880–10890 (2021)
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.061251(2), 3 (2022)
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. pp. 10684–10695 (2022)
Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: A unified embedding for face recognition and clustering. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 815–823 (2015)
Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)
Westerlund, M.: The emergence of deepfake technology: A review. Technology innovation management review 9(11) (2019)
Zheng, Y., Yang, H., Zhang, T., Bao, J., Chen, D., Huang, Y., Yuan, L., Chen, D., Zeng, M., Wen, F.: General facial representation learning in a visual-linguistic manner. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 18697–18709 (2022)
Acknowledgment
This work was supported by the IITP grant (IITP-2024-RS-2022-00156389) funded by MSIT, and the Digital Innovation Hub project (DBSD1-04) supervised by DIP, funded by MSIT and Daegu City, 2024. * MSIT: Ministry of Science and ICT
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Shaheryar, M., Taek Lee, J., Ki Jung, S. (2025). IDDiffuse: Dual-Conditional Diffusion Model for Enhanced Facial Image Anonymization. In: Cho, M., Laptev, I., Tran, D., Yao, A., Zha, H. (eds) Computer Vision – ACCV 2024. ACCV 2024. Lecture Notes in Computer Science, vol 15475. Springer, Singapore. https://doi.org/10.1007/978-981-96-0911-6_25
Download citation
DOI: https://doi.org/10.1007/978-981-96-0911-6_25
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-96-0910-9
Online ISBN: 978-981-96-0911-6
eBook Packages: Computer ScienceComputer Science (R0)