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.
@article{arxiv.2603.16447,
title = {ProgressiveAvatars: Progressive Animatable 3D Gaussian Avatars},
author = {Kaiwen Song and Jinkai Cui and Juyong Zhang},
journal= {arXiv preprint arXiv:2603.16447},
year = {2026}
}
Comments
Accepted to CVPR 2026, Project page: https://ustc3dv.github.io/ProgressiveAvatars/