ProgressiveAvatars: Progressive Animatable 3D Gaussian Avatars

2026-03-17

AI Summary

This work addresses the challenge of dynamically varying network and computational resources in real-time extended reality (XR) and telepresence applications by introducing a multi-level 3D Gaussian avatar representation. The proposed method leverages an adaptive implicit subdivision based on a template mesh, defining Gaussian distributions in local patch coordinate systems to enable expression- and pose-driven animation across levels of detail. By integrating screen-space importance estimation, the framework supports dynamic, progressive refinement of visual fidelity. To the best of our knowledge, this is the first approach to realize progressively loadable, renderable, and animatable 3D Gaussian avatars. Through importance-based scheduling, it smoothly enhances visual quality under constrained bandwidth and compute budgets, achieving an effective balance among low latency, high visual fidelity, and fluidly animated rendering.

Technology Category

• Computer Vision: 3D Computer Vision
• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

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.

Problem

• progressive representation
• 3D avatars
• real-time XR
• telepresence
• resource fluctuation

Innovation

• progressive representation
• 3D Gaussians
• animatable avatars
• adaptive subdivision
• incremental rendering