高斯像素编码头像：一种高效的渲染混合表示
Gaussian Pixel Codec Avatars: A Hybrid Representation for Efficient Rendering
AI总结：
GPiCA通过结合三角网格和各向异性3D高斯，实现高效渲染的逼真头像生成
摘要：
我们提出了高斯像素编码头像（GPiCA），这是一种可以从多视角图像生成并高效在移动设备上渲染的逼真头像。GPiCA采用了一种独特的混合表示方法，结合了三角网格和各向异性3D高斯。这种结合在最大化内存和渲染效率的同时，保持了逼真的外观。三角网格在表示面部皮肤等表面区域时非常高效，而3D高斯则有效处理如头发和胡须等非表面区域。为此，我们开发了一个统一的可微分渲染管道，将网格视为体积渲染范式中3D高斯点绘的半透明层。我们训练神经网络将面部表情代码解码为三个组成部分：3D面部网格、RGBA纹理和一组3D高斯。这些组件在统一的渲染引擎中同时渲染。网络通过多视角图像监督进行训练。我们的结果表明，GPiCA在实现纯高斯基头像的逼真度的同时，达到了基于网格的头像的渲染性能。
英文摘要：
We present Gaussian Pixel Codec Avatars (GPiCA), photorealistic head avatars that can be generated from multi-view images and efficiently rendered on mobile devices. GPiCA utilizes a unique hybrid representation that combines a triangle mesh and anisotropic 3D Gaussians. This combination maximizes memory and rendering efficiency while maintaining a photorealistic appearance. The triangle mesh is highly efficient in representing surface areas like facial skin, while the 3D Gaussians effectively handle non-surface areas such as hair and beard. To this end, we develop a unified differentiable rendering pipeline that treats the mesh as a semi-transparent layer within the volumetric rendering paradigm of 3D Gaussian Splatting. We train neural networks to decode a facial expression code into three components: a 3D face mesh, an RGBA texture, and a set of 3D Gaussians. These components are rendered simultaneously in a unified rendering engine. The networks are trained using multi-view image supervision. Our results demonstrate that GPiCA achieves the realism of purely Gaussian-based avatars while matching the rendering performance of mesh-based avatars.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
