TEDRA: Text-based Editing of Dynamic and Photoreal Actors
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909299412828160 |
|---|---|
| author | Sunagad, Basavaraj Zhu, Heming Mendiratta, Mohit Kortylewski, Adam Theobalt, Christian Habermann, Marc |
| author_facet | Sunagad, Basavaraj Zhu, Heming Mendiratta, Mohit Kortylewski, Adam Theobalt, Christian Habermann, Marc |
| contents | Over the past years, significant progress has been made in creating photorealistic and drivable 3D avatars solely from videos of real humans. However, a core remaining challenge is the fine-grained and user-friendly editing of clothing styles by means of textual descriptions. To this end, we present TEDRA, the first method allowing text-based edits of an avatar, which maintains the avatar's high fidelity, space-time coherency, as well as dynamics, and enables skeletal pose and view control. We begin by training a model to create a controllable and high-fidelity digital replica of the real actor. Next, we personalize a pretrained generative diffusion model by fine-tuning it on various frames of the real character captured from different camera angles, ensuring the digital representation faithfully captures the dynamics and movements of the real person. This two-stage process lays the foundation for our approach to dynamic human avatar editing. Utilizing this personalized diffusion model, we modify the dynamic avatar based on a provided text prompt using our Personalized Normal Aligned Score Distillation Sampling (PNA-SDS) within a model-based guidance framework. Additionally, we propose a time step annealing strategy to ensure high-quality edits. Our results demonstrate a clear improvement over prior work in functionality and visual quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_15995 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TEDRA: Text-based Editing of Dynamic and Photoreal Actors Sunagad, Basavaraj Zhu, Heming Mendiratta, Mohit Kortylewski, Adam Theobalt, Christian Habermann, Marc Computer Vision and Pattern Recognition Over the past years, significant progress has been made in creating photorealistic and drivable 3D avatars solely from videos of real humans. However, a core remaining challenge is the fine-grained and user-friendly editing of clothing styles by means of textual descriptions. To this end, we present TEDRA, the first method allowing text-based edits of an avatar, which maintains the avatar's high fidelity, space-time coherency, as well as dynamics, and enables skeletal pose and view control. We begin by training a model to create a controllable and high-fidelity digital replica of the real actor. Next, we personalize a pretrained generative diffusion model by fine-tuning it on various frames of the real character captured from different camera angles, ensuring the digital representation faithfully captures the dynamics and movements of the real person. This two-stage process lays the foundation for our approach to dynamic human avatar editing. Utilizing this personalized diffusion model, we modify the dynamic avatar based on a provided text prompt using our Personalized Normal Aligned Score Distillation Sampling (PNA-SDS) within a model-based guidance framework. Additionally, we propose a time step annealing strategy to ensure high-quality edits. Our results demonstrate a clear improvement over prior work in functionality and visual quality. |
| title | TEDRA: Text-based Editing of Dynamic and Photoreal Actors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.15995 |