单张照片生成可控制的高保真3D头像，实时渲染达90帧。
Reconstruction and Reenactment Separated Method for Realistic Gaussian Head
- 分离重建与驱动流程，用单图生成高质量3D高斯头像。
- 512x512分辨率下实现90帧/秒的实时渲染，轻量驱动模型不降效。
- 参数规模越大性能越好，适合需要高效可控虚拟头像的场景。
本文提出一种针对3D高斯头像的重建与重演分离框架，仅需单张肖像图即可生成可控制的虚拟化身。我们基于WebSSL构建了大规模单图像高斯头像生成器，并采用两阶段训练方法，显著提升模型泛化能力与高频纹理重建效果。推理时，由控制信号驱动的超轻量级高斯化身可在512x512分辨率下实现90帧/秒的高速渲染。进一步实验表明，该框架遵循缩放定律：增大重建模块参数量可提升性能，而分离设计确保驱动效率不受影响。大量定量与定性实验验证，本方法优于当前最先进水平。
原文摘要 · Abstract (English)
In this paper, we explore a reconstruction and reenactment separated framework for 3D Gaussians head, which requires only a single portrait image as input to generate controllable avatar. Specifically, we developed a large-scale one-shot gaussian head generator built upon WebSSL and employed a two-stage training approach that significantly enhances the capabilities of generalization and high-frequency texture reconstruction. During inference, an ultra-lightweight gaussian avatar driven by control signals enables high frame-rate rendering, achieving 90 FPS at a resolution of 512x512. We further demonstrate that the proposed framework follows the scaling law, whereby increasing the parameter scale of the reconstruction module leads to improved performance. Moreover, thanks to the separation design, driving efficiency remains unaffected. Finally, extensive quantitative and qualitative experiments validate that our approach outperforms current state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。