Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2408.00296 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911974496927744 |
|---|---|
| author | He, Yuxiao Zhuang, Yiyu Wang, Yanwen Yao, Yao Zhu, Siyu Li, Xiaoyu Zhang, Qi Cao, Xun Zhu, Hao |
| author_facet | He, Yuxiao Zhuang, Yiyu Wang, Yanwen Yao, Yao Zhu, Siyu Li, Xiaoyu Zhang, Qi Cao, Xun Zhu, Hao |
| contents | Creating a 360° parametric model of a human head is a very challenging task. While recent advancements have demonstrated the efficacy of leveraging synthetic data for building such parametric head models, their performance remains inadequate in crucial areas such as expression-driven animation, hairstyle editing, and text-based modifications. In this paper, we build a dataset of artist-designed high-fidelity human heads and propose to create a novel parametric 360° renderable parametric head model from it. Our scheme decouples the facial motion/shape and facial appearance, which are represented by a classic parametric 3D mesh model and an attached neural texture, respectively. We further propose a training method for decompositing hairstyle and facial appearance, allowing free-swapping of the hairstyle. A novel inversion fitting method is presented based on single image input with high generalization and fidelity. To the best of our knowledge, our model is the first parametric 3D full-head that achieves 360° free-view synthesis, image-based fitting, appearance editing, and animation within a single model. Experiments show that facial motions and appearances are well disentangled in the parametric space, leading to SOTA performance in rendering and animating quality. The code and SynHead100 dataset are released at https://nju-3dv.github.io/projects/Head360. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00296 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360° He, Yuxiao Zhuang, Yiyu Wang, Yanwen Yao, Yao Zhu, Siyu Li, Xiaoyu Zhang, Qi Cao, Xun Zhu, Hao Computer Vision and Pattern Recognition Creating a 360° parametric model of a human head is a very challenging task. While recent advancements have demonstrated the efficacy of leveraging synthetic data for building such parametric head models, their performance remains inadequate in crucial areas such as expression-driven animation, hairstyle editing, and text-based modifications. In this paper, we build a dataset of artist-designed high-fidelity human heads and propose to create a novel parametric 360° renderable parametric head model from it. Our scheme decouples the facial motion/shape and facial appearance, which are represented by a classic parametric 3D mesh model and an attached neural texture, respectively. We further propose a training method for decompositing hairstyle and facial appearance, allowing free-swapping of the hairstyle. A novel inversion fitting method is presented based on single image input with high generalization and fidelity. To the best of our knowledge, our model is the first parametric 3D full-head that achieves 360° free-view synthesis, image-based fitting, appearance editing, and animation within a single model. Experiments show that facial motions and appearances are well disentangled in the parametric space, leading to SOTA performance in rendering and animating quality. The code and SynHead100 dataset are released at https://nju-3dv.github.io/projects/Head360. |
| title | Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360° |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.00296 |