Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining

Abstract

High-quality 3D avatar modeling faces a critical trade-off between fidelity and generalization. We present Large-Scale Codec Avatars (LCA), a high-fidelity, full-body 3D avatar model that generalizes to world-scale populations in a feedforward manner. Inspired by LLMs and vision foundation models, we present a pre/post-training paradigm: pretrain on 1M in-the-wild videos to learn broad priors over appearance and geometry, then post-train on high-quality curated data to enhance expressivity and fidelity. LCA generalizes across hair styles, clothing, and demographics while providing precise facial expressions and finger-level articulation control.