← 研踪 PaperTrailCVF · CVPR 2026:cvf:875e2165a1587f2f8787574a641b1d52 · 记录 #1
Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
Li, JunxuanKhirodkar, RawalZakharov, EgorLee, JihyunSu, ZhaoenDong, YuanMartinez, JulietaLi, KaiTan, QingyangShiratori, TakaakiHu, MatthewGuo, PeihongHuang, XuhuaJiang, ZhongshiYang, LingchenZarei, AriyanPesavento, MarcoXu, YichenHe, ChenganWen, HeNam, GiljooDeng, TengBorsos, WyattThakrar, AnjaliBazin, Jean-CharlesAbdrashitov, RinatStoll, CarstenHidalgo, GinésBooth, JamesWang, LucyMa, XiaowenRong, YuThalanki, SairanjithCao, ChenHäne, ChristianKar, AbhishekBouaziz, SofienSaragih, JasonSheikh, YaserSaito, Shunsuke 来源日期（仅到年份） 2026
来源记录日期 2026
雷达观测 2026-11-05 03:08
摘要
High-quality 3D avatar modeling faces a critical trade-off between fidelity and generalization. On the one hand, multi-view studio data enables high-fidelity modeling of humans with precise control over expressions and poses, but it struggles to generalize to real-world data due to limited scale and the domain gap between the studio environment and the real world. On the other hand, recent large-scale avatar models trained on millions of in-the-wild samples show promise for generalization across a wide range of identities, yet the resulting avatars are often of low-quality due to inherent 3D ambiguities. To address this, 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, enabling efficient inference. Inspired by the success of large language models and vision foundation models, we present, for the first time, a pre/post-training paradigm for 3D avatar modeling at scale: we 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, fine-grained facial expressions and finger-level articulation control, with strong identity preservation. Notably, we observe emergent generalization to relightability and loose garment support to unconstrained inputs, and zero-shot robustness to stylized imagery, despite the absence of direct supervision.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
High-quality 3D avatar modeling faces a critical trade-off between fidelity and generalization. On the one hand, multi-view studio data enables high-fidelity modeling of humans with precise control over expressions and poses, but it struggles to generalize to real-world data due to limited scale and the domain gap between the studio environment and the real world. On the other hand, recent large-scale avatar models trained on millions of in-the-wild samples show promise for generalization across a wide range of identities, yet the resulting avatars are often of low-quality due to inherent 3D ambiguities. To address this, 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, enabling efficient inference. Inspired by the success of large language models and vision foundation models, we present, for the first time, a pre/post-training paradigm for 3D avatar modeling at scale: we 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, fine-grained facial expressions and finger-level articulation control, with strong identity preservation. Notably, we observe emergent generalization to relightability and loose garment support to unconstrained inputs, and zero-shot robustness to stylized imagery, despite the absence of direct supervision.
查看此版本解读 →查看此版本原文 ↗