One2Avatar: Generative Implicit Head Avatar For Few-shot User Adaptation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913237089386496 |
|---|---|
| author | Yu, Zhixuan Bai, Ziqian Meka, Abhimitra Tan, Feitong Xu, Qiangeng Pandey, Rohit Fanello, Sean Park, Hyun Soo Zhang, Yinda |
| author_facet | Yu, Zhixuan Bai, Ziqian Meka, Abhimitra Tan, Feitong Xu, Qiangeng Pandey, Rohit Fanello, Sean Park, Hyun Soo Zhang, Yinda |
| contents | Traditional methods for constructing high-quality, personalized head avatars from monocular videos demand extensive face captures and training time, posing a significant challenge for scalability. This paper introduces a novel approach to create high quality head avatar utilizing only a single or a few images per user. We learn a generative model for 3D animatable photo-realistic head avatar from a multi-view dataset of expressions from 2407 subjects, and leverage it as a prior for creating personalized avatar from few-shot images. Different from previous 3D-aware face generative models, our prior is built with a 3DMM-anchored neural radiance field backbone, which we show to be more effective for avatar creation through auto-decoding based on few-shot inputs. We also handle unstable 3DMM fitting by jointly optimizing the 3DMM fitting and camera calibration that leads to better few-shot adaptation. Our method demonstrates compelling results and outperforms existing state-of-the-art methods for few-shot avatar adaptation, paving the way for more efficient and personalized avatar creation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11909 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | One2Avatar: Generative Implicit Head Avatar For Few-shot User Adaptation Yu, Zhixuan Bai, Ziqian Meka, Abhimitra Tan, Feitong Xu, Qiangeng Pandey, Rohit Fanello, Sean Park, Hyun Soo Zhang, Yinda Computer Vision and Pattern Recognition Traditional methods for constructing high-quality, personalized head avatars from monocular videos demand extensive face captures and training time, posing a significant challenge for scalability. This paper introduces a novel approach to create high quality head avatar utilizing only a single or a few images per user. We learn a generative model for 3D animatable photo-realistic head avatar from a multi-view dataset of expressions from 2407 subjects, and leverage it as a prior for creating personalized avatar from few-shot images. Different from previous 3D-aware face generative models, our prior is built with a 3DMM-anchored neural radiance field backbone, which we show to be more effective for avatar creation through auto-decoding based on few-shot inputs. We also handle unstable 3DMM fitting by jointly optimizing the 3DMM fitting and camera calibration that leads to better few-shot adaptation. Our method demonstrates compelling results and outperforms existing state-of-the-art methods for few-shot avatar adaptation, paving the way for more efficient and personalized avatar creation. |
| title | One2Avatar: Generative Implicit Head Avatar For Few-shot User Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.11909 |