RID-TWIN: An end-to-end pipeline for automatic face de-identification in videos

arXiv:2403.10058v1 Announce Type: new
Abstract: Face de-identification in videos is a challenging task in the domain of computer vision, primarily used in privacy-preserving applications. Despite the considerable progress achieved through generative vision models, there remain multiple challenges in the latest approaches. They lack a comprehensive discussion and evaluation of aspects such as realism, temporal coherence, and preservation of non-identifiable features. In our work, we propose RID-Twin: a novel pipeline that leverages the state-of-the-art generative models, and decouples identity from motion …

abstract applications arxiv challenges computer computer vision cs.cv de-identification domain evaluation face generative identification multiple pipeline privacy progress through twin type videos vision vision models