FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911652399546368 |
|---|---|
| author | Wang, Yuanzhi Ren, Xuhua Cheng, Jiaxiang Ma, Bing Yu, Kai Liang, Sen Li, Wenyue Zheng, Tianxiang Lu, Qinglin Cui, Zhen |
| author_facet | Wang, Yuanzhi Ren, Xuhua Cheng, Jiaxiang Ma, Bing Yu, Kai Liang, Sen Li, Wenyue Zheng, Tianxiang Lu, Qinglin Cui, Zhen |
| contents | Identity-preserving text-to-video generation (IPT2V) empowers users to produce diverse and imaginative videos with consistent human facial identity. Despite recent progress, existing methods often suffer from significant identity distortion under large facial pose variations or facial occlusions. In this paper, we propose \textit{FaithfulFaces}, a pose-faithful facial identity preservation learning framework to improve IPT2V in complex dynamic scenes. The key of FaithfulFaces is a pose-shared identity aligner that refines and aligns facial poses across distinct views via a pose-shared dictionary and a pose variation-identity invariance constraint. By mapping single-view inputs into a global facial pose representation with explicit Euler angle embeddings, FaithfulFaces provides a pose-faithful facial prior that guides generative foundations toward robust identity-preserving generation. In particular, we develop a specialized pipeline to curate a high-quality video dataset featuring substantial facial pose diversity. Extensive experiments demonstrate that FaithfulFaces achieves state-of-the-art performance, maintaining superior identity consistency and structural clarity even as pose changes and occlusions occur. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_04702 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation Wang, Yuanzhi Ren, Xuhua Cheng, Jiaxiang Ma, Bing Yu, Kai Liang, Sen Li, Wenyue Zheng, Tianxiang Lu, Qinglin Cui, Zhen Computer Vision and Pattern Recognition Artificial Intelligence Identity-preserving text-to-video generation (IPT2V) empowers users to produce diverse and imaginative videos with consistent human facial identity. Despite recent progress, existing methods often suffer from significant identity distortion under large facial pose variations or facial occlusions. In this paper, we propose \textit{FaithfulFaces}, a pose-faithful facial identity preservation learning framework to improve IPT2V in complex dynamic scenes. The key of FaithfulFaces is a pose-shared identity aligner that refines and aligns facial poses across distinct views via a pose-shared dictionary and a pose variation-identity invariance constraint. By mapping single-view inputs into a global facial pose representation with explicit Euler angle embeddings, FaithfulFaces provides a pose-faithful facial prior that guides generative foundations toward robust identity-preserving generation. In particular, we develop a specialized pipeline to curate a high-quality video dataset featuring substantial facial pose diversity. Extensive experiments demonstrate that FaithfulFaces achieves state-of-the-art performance, maintaining superior identity consistency and structural clarity even as pose changes and occlusions occur. |
| title | FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.04702 |