LegacyAvatars: Volumetric Face Avatars For Traditional Graphics Pipelines

TL;DR

This paper presents a new volumetric face avatar representation that enables photorealistic rendering and animation using classical graphics pipelines, making high-quality avatars more accessible and efficient for traditional rendering systems.

Contribution

It introduces a novel radiance field-based representation that combines volumetric rendering with explicit layered meshes for efficient, controllable facial avatar rendering on legacy platforms.

Findings

Achieves photorealistic 3D face rendering with controllable features.

Enables efficient streaming and rendering on legacy graphics hardware.

Supports realistic facial animations through simple texture blending.

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.