SpatialAvatar-0：高品質4D頭部虛擬化身的多階段重建技術

摘要

高质量4D头部虚拟形象——由一个或少数源肖像生成——是远程临场、增强现实/虚拟现实以及数字人交互的核心。3D高斯泼溅（3DGS）已成为主导表示方法，其两大互补范式（可泛化的前馈预测器与逐主体精化器）正并行成熟。然而，现有前馈预测器基于单一数据集家族训练，且采用硬编码的源数量，继承了相应的领域偏差；而逐主体精化器需30万至60万次迭代，并依赖自适应致密化过程，该过程会破坏上游高斯布局，导致两种范式无法端到端共享同一表示。为弥合两者，我们提出了SpatialAvatar-0，基于共享的FLAME网格绑定高斯表示：采用无参数K源均值池化前馈生成器，并设计从单目-时序到多视-空间的两阶段调度策略，以锚定身份先验防止其向小规模多视图集坍塌。此外，我们引入了一种仅需1万次迭代的布局保持逐主体精化循环，该循环冻结FLAME绑定与高斯数量，并以三分量反尖峰正则化替代致密化过程。在VFHQ/HDTF跨域零样本测试中，尽管从未在任一测试域训练，我们的方法在PSNR上超越域内领先方法GAGAvatar达1.5 dB；在SplattingAvatar单目基准测试中，我们领先所有已报告指标，以比常见最先进基线快60倍的逐主体调度，超越需30万次迭代的GeoAvatar达1.3 dB PSNR。网站：https://spatialwalk.github.io/SpatialAvatar-0。

English

High-quality 4D head avatars from one or a few source portraits are central to telepresence, AR/VR, and digital-human interaction. 3D Gaussian Splatting (3DGS) has emerged as the dominant representation, with two complementary regimes (generalizable feed-forward predictors and per-subject refiners) maturing in parallel. However, existing feed-forward predictors are trained on a single dataset family with a hard-coded source count, inheriting the corresponding domain bias. Per-subject refiners require 300K--600K iterations and rely on adaptive densification that destroys upstream Gaussian layouts, preventing the two regimes from sharing a representation end-to-end. To bridge both regimes we propose SpatialAvatar-0 on a shared FLAME-mesh-bound Gaussian representation: a feed-forward generator with a parameter-free K-source mean-pool and a monocular-temporal to multi-view-spatial two-phase schedule that anchors against identity-prior collapse onto the smaller multi-view set. We further introduce a 10K-iter layout-preserving per-subject refinement loop that freezes the FLAME-binding and Gaussian count and replaces densification with a three-component anti-spike regularization. On VFHQ/HDTF cross-domain zero-shot we surpass the in-domain leader GAGAvatar by +1.5 dB PSNR despite never training on either test domain, and on the SplattingAvatar monocular benchmark we lead every reported metric, surpassing the 300K-iter GeoAvatar by +1.3 dB PSNR at up to 60x shorter per-subject schedule than common SOTA baselines. Website: https://spatialwalk.github.io/SpatialAvatar-0.