English

Gaussian Deja-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilities

Computer Vision and Pattern Recognition 2024-11-07 v3

Abstract

Recent advancements in 3D Gaussian Splatting (3DGS) have unlocked significant potential for modeling 3D head avatars, providing greater flexibility than mesh-based methods and more efficient rendering compared to NeRF-based approaches. Despite these advancements, the creation of controllable 3DGS-based head avatars remains time-intensive, often requiring tens of minutes to hours. To expedite this process, we here introduce the "Gaussian Deja-vu" framework, which first obtains a generalized model of the head avatar and then personalizes the result. The generalized model is trained on large 2D (synthetic and real) image datasets. This model provides a well-initialized 3D Gaussian head that is further refined using a monocular video to achieve the personalized head avatar. For personalizing, we propose learnable expression-aware rectification blendmaps to correct the initial 3D Gaussians, ensuring rapid convergence without the reliance on neural networks. Experiments demonstrate that the proposed method meets its objectives. It outperforms state-of-the-art 3D Gaussian head avatars in terms of photorealistic quality as well as reduces training time consumption to at least a quarter of the existing methods, producing the avatar in minutes.

Keywords

Cite

@article{arxiv.2409.16147,
  title  = {Gaussian Deja-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilities},
  author = {Peizhi Yan and Rabab Ward and Qiang Tang and Shan Du},
  journal= {arXiv preprint arXiv:2409.16147},
  year   = {2024}
}

Comments

11 pages, Accepted by WACV 2025 in Round 1

R2 v1 2026-06-28T18:55:24.868Z