GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909153446854656 |
|---|---|
| author | Qian, Shenhan Kirschstein, Tobias Schoneveld, Liam Davoli, Davide Giebenhain, Simon Nießner, Matthias |
| author_facet | Qian, Shenhan Kirschstein, Tobias Schoneveld, Liam Davoli, Davide Giebenhain, Simon Nießner, Matthias |
| contents | We introduce GaussianAvatars, a new method to create photorealistic head avatars that are fully controllable in terms of expression, pose, and viewpoint. The core idea is a dynamic 3D representation based on 3D Gaussian splats that are rigged to a parametric morphable face model. This combination facilitates photorealistic rendering while allowing for precise animation control via the underlying parametric model, e.g., through expression transfer from a driving sequence or by manually changing the morphable model parameters. We parameterize each splat by a local coordinate frame of a triangle and optimize for explicit displacement offset to obtain a more accurate geometric representation. During avatar reconstruction, we jointly optimize for the morphable model parameters and Gaussian splat parameters in an end-to-end fashion. We demonstrate the animation capabilities of our photorealistic avatar in several challenging scenarios. For instance, we show reenactments from a driving video, where our method outperforms existing works by a significant margin. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_02069 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians Qian, Shenhan Kirschstein, Tobias Schoneveld, Liam Davoli, Davide Giebenhain, Simon Nießner, Matthias Computer Vision and Pattern Recognition We introduce GaussianAvatars, a new method to create photorealistic head avatars that are fully controllable in terms of expression, pose, and viewpoint. The core idea is a dynamic 3D representation based on 3D Gaussian splats that are rigged to a parametric morphable face model. This combination facilitates photorealistic rendering while allowing for precise animation control via the underlying parametric model, e.g., through expression transfer from a driving sequence or by manually changing the morphable model parameters. We parameterize each splat by a local coordinate frame of a triangle and optimize for explicit displacement offset to obtain a more accurate geometric representation. During avatar reconstruction, we jointly optimize for the morphable model parameters and Gaussian splat parameters in an end-to-end fashion. We demonstrate the animation capabilities of our photorealistic avatar in several challenging scenarios. For instance, we show reenactments from a driving video, where our method outperforms existing works by a significant margin. |
| title | GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.02069 |