Back to Search
Start Over
Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians
- Publication Year :
- 2023
-
Abstract
- Creating high-fidelity 3D head avatars has always been a research hotspot, but there remains a great challenge under lightweight sparse view setups. In this paper, we propose Gaussian Head Avatar represented by controllable 3D Gaussians for high-fidelity head avatar modeling. We optimize the neutral 3D Gaussians and a fully learned MLP-based deformation field to capture complex expressions. The two parts benefit each other, thereby our method can model fine-grained dynamic details while ensuring expression accuracy. Furthermore, we devise a well-designed geometry-guided initialization strategy based on implicit SDF and Deep Marching Tetrahedra for the stability and convergence of the training procedure. Experiments show our approach outperforms other state-of-the-art sparse-view methods, achieving ultra high-fidelity rendering quality at 2K resolution even under exaggerated expressions.<br />Comment: Projectpage: https://yuelangx.github.io/gaussianheadavatar, Code: https://github.com/YuelangX/Gaussian-Head-Avatar
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2312.03029
- Document Type :
- Working Paper