Total-Editing：具有可编辑外观、动作和光照的头部化身
Total-Editing: Head Avatar with Editable Appearance, Motion, and Lighting
AI总结：
Total-Editing提出统一肖像编辑框架，结合神经辐射场内在分解与移动最小二乘变形场，实现外观、动作和光照的精确控制，提升编辑质量与真实感。
摘要：
面部重演和肖像重光照是肖像编辑中的关键任务，然而它们通常被独立处理，缺乏协同性。大多数面部重演方法优先考虑动作控制和多视角一致性，而肖像重光照则侧重于调整阴影效果。为了同时利用几何一致性和光照感知，我们提出了Total-Editing，一个统一的肖像编辑框架，能够对外观、动作和光照进行精确控制。具体而言，我们设计了一个具有内在分解能力的神经辐射场解码器，使得来自肖像图像或HDR环境贴图的光照信息能够无缝集成到合成肖像中。我们还引入了一个基于移动最小二乘的变形场，以增强化身动作和阴影效果的时空连贯性。凭借这些创新，我们的统一框架显著提升了肖像编辑结果的质量和真实感。此外，Total-Editing的多源特性支持更灵活的应用，例如将一个肖像的光照转移到另一个肖像，或使用自定义背景进行肖像动画化。
英文摘要：
Face reenactment and portrait relighting are essential tasks in portrait editing, yet they are typically addressed independently, without much synergy. Most face reenactment methods prioritize motion control and multiview consistency, while portrait relighting focuses on adjusting shading effects. To take advantage of both geometric consistency and illumination awareness, we introduce Total-Editing, a unified portrait editing framework that enables precise control over appearance, motion, and lighting. Specifically, we design a neural radiance field decoder with intrinsic decomposition capabilities. This allows seamless integration of lighting information from portrait images or HDR environment maps into synthesized portraits. We also incorporate a moving least squares based deformation field to enhance the spatiotemporal coherence of avatar motion and shading effects. With these innovations, our unified framework significantly improves the quality and realism of portrait editing results. Further, the multi-source nature of Total-Editing supports more flexible applications, such as illumination transfer from one portrait to another, or portrait animation with customized backgrounds.
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。
