RID-TWIN: An end-to-end pipeline for automatic face de-identification in videos
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916160259227648 |
|---|---|
| author | Mukherjee, Anirban Choudhury, Monjoy Narayan Jayagopi, Dinesh Babu |
| author_facet | Mukherjee, Anirban Choudhury, Monjoy Narayan Jayagopi, Dinesh Babu |
| contents | 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 to perform automatic face de-identification in videos. We investigate the task from a holistic point of view and discuss how our approach addresses the pertinent existing challenges in this domain. We evaluate the performance of our methodology on the widely employed VoxCeleb2 dataset, and also a custom dataset designed to accommodate the limitations of certain behavioral variations absent in the VoxCeleb2 dataset. We discuss the implications and advantages of our work and suggest directions for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_10058 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RID-TWIN: An end-to-end pipeline for automatic face de-identification in videos Mukherjee, Anirban Choudhury, Monjoy Narayan Jayagopi, Dinesh Babu Computer Vision and Pattern Recognition 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 to perform automatic face de-identification in videos. We investigate the task from a holistic point of view and discuss how our approach addresses the pertinent existing challenges in this domain. We evaluate the performance of our methodology on the widely employed VoxCeleb2 dataset, and also a custom dataset designed to accommodate the limitations of certain behavioral variations absent in the VoxCeleb2 dataset. We discuss the implications and advantages of our work and suggest directions for future research. |
| title | RID-TWIN: An end-to-end pipeline for automatic face de-identification in videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.10058 |