LegacyAvatars

Volumetric Face Avatars For Traditional Graphics Pipelines

Safa C. Medin1,2, Gengyan Li1,3, Ziqian Bai1, Ruofei Du1, Leonhard Helminger1, Yinda Zhang1,
Stephan Garbin1, Philip Davidson1, Gregory W. Wornell2, Thabo Beeler1, Abhimitra Meka1
1Google, 2MIT, 3ETH Zurich
arXiv Paper

Abstract

We introduce a novel representation for efficient classical rendering of photorealistic 3D face avatars. Leveraging recent advances in radiance fields anchored to parametric face models, our approach achieves controllable volumetric rendering of complex facial features, including hair, skin, and eyes. At enrollment time, we learn a set of radiance manifolds in 3D space to extract an explicit layered mesh, along with appearance and warp textures. During deployment, this allows us to control and animate the face through simple linear blending and alpha compositing of textures over a static mesh. This explicit representation also enables the generated avatar to be efficiently streamed online and then rendered using classical mesh and shader-based rendering on legacy graphics platforms, eliminating the need for any custom engineering or integration.


Methodology

From an enrollment sequence of a subject, we learn a layered mesh and blend-textures that model the geometry, appearance and deformations, and a simple linear transformation that maps tracked face model parameters to blend weights. Our representation is readily compatible with existing streaming infrastructure and can be deployed in traditional graphics pipelines in a device- and platform-agnostic way.


View Synthesis and Animation


Real-time Rendering on Web Browsers

Our model can be deployed to traditional graphics engines on web browsers, achieving native cross-platform compatibility without the need for custom ML inference or specialized hardware.


BibTeX Citation

@article{medin2026legacyavatars,
  author    = {Medin, Safa C. and Li, Gengyan and Bai, Ziqian and Du, Ruofei and Helminger, Leonhard and Zhang, Yinda and Garbin, Stephan and Davidson, Philip and Wornell, Gregory W. and Beeler, Thabo and Meka, Abhimitra},
  title     = {{LegacyAvatars: Volumetric Face Avatars For Traditional Graphics Pipelines}},
  journal   = {International Conference on 3D Vision (3DV)},
  year      = {2026},
}