GeoDiff4D：面向 4D 头部化身重建的几何感知扩散
GeoDiff4D: Geometry-Aware Diffusion for 4D Head Avatar Reconstruction
把扩散模型同时合成肖像图与表面法线，作为几何先验蒸馏进 3D 高斯化身，为单图重建提供了一条「用生成模型补几何」的可复用路径；其无姿态表情编码器也可直接用于驱动类任务。
原文依据 jointly synthesizes portrait images and corresponding surface normals, while a pose-free expression encoder captures implicit expression representations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从单张肖像图像重建照片级真实且可动画驱动的 4D 头部化身，仍是计算机视觉中的一项基础性挑战。尽管扩散模型已在图像与视频生成方面推动了化身重建的显著进展，现有方法主要依赖二维先验，难以获得一致的三维几何。我们提出一种新框架，利用几何感知扩散为高保真头部化身重建蒸馏出强几何先验。该方法联合合成肖像图像与对应的表面法线，同时由无姿态表情编码器捕获隐式表情表示。合成图像与表情潜变量均被蒸馏进基于三维高斯的化身中，从而实现兼具照片级真实渲染与准确几何的化身。大量实验表明，本方法在视觉质量、表情保真度与跨身份泛化能力上大幅优于最优方法，并支持实时渲染。
英文原文摘要 1031 字符
Reconstructing photorealistic and animatable 4D head avatars from a single portrait image remains a fundamental challenge in computer vision. While diffusion models have enabled remarkable progress in image and video generation for avatar reconstruction, existing methods primarily rely on 2D priors and struggle to achieve consistent 3D geometry. We propose a novel framework that leverages geometry-aware diffusion to distill strong geometry priors for high-fidelity head avatar reconstruction. Our approach jointly synthesizes portrait images and corresponding surface normals, while a pose-free expression encoder captures implicit expression representations. Both synthesized images and expression latents are distilled into 3D Gaussian-based avatars, enabling photorealistic rendering with accurate geometry. Extensive experiments demonstrate that our method substantially outperforms state-of-the-art approaches in visual quality, expression fidelity, and cross-identity generalization, while supporting real-time rendering.