CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks
This addresses privacy concerns in real-world scenarios like people tracking or action recognition, offering a controlled and diverse anonymization method.
The paper tackles the problem of protecting people's identity in images and videos for computer vision tasks by proposing CIAGAN, a model for conditional identity anonymization using generative adversarial networks, which achieves state-of-the-art results in producing high-quality anonymized data.
The unprecedented increase in the usage of computer vision technology in society goes hand in hand with an increased concern in data privacy. In many real-world scenarios like people tracking or action recognition, it is important to be able to process the data while taking careful consideration in protecting people's identity. We propose and develop CIAGAN, a model for image and video anonymization based on conditional generative adversarial networks. Our model is able to remove the identifying characteristics of faces and bodies while producing high-quality images and videos that can be used for any computer vision task, such as detection or tracking. Unlike previous methods, we have full control over the de-identification (anonymization) procedure, ensuring both anonymization as well as diversity. We compare our method to several baselines and achieve state-of-the-art results.