| title | SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction |
|---|---|
| authors | Yiran Wang, Zeyu Zhang, Yuanming Li, Ziming Wang, Yang Zhao |
| date | 2026-06-14 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.15659 |
| upvotes | 5 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | 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. |
cite
@misc{wang2026spatialavatar,
title={SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction},
author={Yiran Wang and Zeyu Zhang and Yuanming Li and Ziming Wang and Yang Zhao},
year={2026},
eprint={2606.15659},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.15659}
}