Header logo is

TADA! Text to Animatable Digital Avatars

2024

Conference Paper

ps


We introduce TADA, a simple-yet-effective approach that takes textual descriptions and produces expressive 3D avatars with high-quality geometry and lifelike textures, that can be animated and rendered with traditional graphics pipelines. Existing text-based character generation methods are limited in terms of geometry and texture quality, and cannot be realistically animated due to inconsistent align-007 ment between the geometry and the texture, particularly in the face region. To overcome these limitations, TADA leverages the synergy of a 2D diffusion model and an animatable parametric body model. Specifically, we derive an optimizable high-resolution body model from SMPL-X with 3D displacements and a texture map, and use hierarchical rendering with score distillation sampling (SDS) to create high-quality, detailed, holistic 3D avatars from text. To ensure alignment between the geometry and texture, we render normals and RGB images of the generated character and exploit their latent embeddings in the SDS training process. We further introduce various expression parameters to deform the generated character during training, ensuring that the semantics of our generated character remain consistent with the original SMPL-X model, resulting in an animatable character. Comprehensive evaluations demonstrate that TADA significantly surpasses existing approaches on both qualitative and quantitative measures. TADA enables creation of large-scale digital character assets that are ready for animation and rendering, while also being easily editable through natural language. The code will be public for research purposes.

Author(s): Tingting Liao and Hongwei Yi and Yuliang Xiu and Jiaxiang Tang and Yangyi Huang and Justus Thies and Michael J. Black
Book Title: International Conference on 3D Vision (3DV 2024)
Year: 2024
Month: March

Department(s): Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Event Name: 3DV 2024
Event Place: Davos, Switzerland

State: Accepted

Links: Home
Code
Video
Video:

BibTex

@inproceedings{tada2024,
  title = {{TADA!} Text to Animatable Digital Avatars},
  author = {Liao, Tingting and Yi, Hongwei and Xiu, Yuliang and Tang, Jiaxiang and Huang, Yangyi and Thies, Justus and Black, Michael J.},
  booktitle = {International Conference on 3D Vision (3DV 2024)},
  month = mar,
  year = {2024},
  doi = {},
  month_numeric = {3}
}