ProgressiveAvatars: Progressive Animatable 3D Gaussian Avatars

TL;DR

ProgressiveAvatars introduces a hierarchical, animatable 3D Gaussian avatar system that adapts to fluctuating network and computational resources, enabling smooth progressive delivery and rendering in real-time XR applications.

Contribution

It presents a novel hierarchical 3D Gaussian representation that supports progressive loading, rendering, and animation under resource constraints, improving real-time XR experiences.

Findings

Supports incremental loading and rendering of avatars

Enables smooth quality improvements with bandwidth fluctuations

Maintains animation fidelity across multiple detail levels

Abstract

In practical real-time XR and telepresence applications, network and computing resources fluctuate frequently. Therefore, a progressive 3D representation is needed. To this end, we propose ProgressiveAvatars, a progressive avatar representation built on a hierarchy of 3D Gaussians grown by adaptive implicit subdivision on a template mesh. 3D Gaussians are defined in face-local coordinates to remain animatable under varying expressions and head motion across multiple detail levels. The hierarchy expands when screen-space signals indicate a lack of detail, allocating resources to important areas. Leveraging importance ranking, ProgressiveAvatars supports incremental loading and rendering, adding new Gaussians as they arrive while preserving previous content, thus achieving smooth quality improvements across varying bandwidths. ProgressiveAvatars enables progressive delivery and progressive rendering under fluctuating network bandwidth and varying compute and memory resources.