FaceCam：通过尺度感知条件实现肖像视频相机控制
FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning
提出一种人脸定制的尺度感知相机表示，无需3D先验即可实现确定性的相机条件控制，可复用于其他需要精确相机轨迹控制的视频生成任务，避免几何失真。
原文依据 we propose a face-tailored scale-aware representation for camera transformations that provides deterministic conditioning without relying on 3D priors.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出FaceCam，一个针对单目人像视频输入、可根据可定制相机轨迹生成视频的系统。近期基于大型视频生成模型的相机控制方法已展现出良好进展，但由于尺度模糊的相机表示或3D重建误差，这些方法在人像视频上常出现几何失真和视觉伪影。为克服这些局限，我们提出一种人脸定制的尺度感知相机变换表示，无需依赖3D先验即可提供确定性条件。我们在多视角影棚拍摄和野外单目视频上训练视频生成模型，并引入两种相机控制数据生成策略：合成相机运动和多镜头拼接，以利用静态训练相机并在推理时泛化到动态、连续的相机轨迹。在Ava-256数据集和多样化的野外视频上的实验表明，FaceCam在相机可控性、视觉质量、身份和运动保持方面取得了优越性能。
英文原文摘要 1100 字符
We introduce FaceCam, a system that generates video under customizable camera trajectories for monocular human portrait video input. Recent camera control approaches based on large video-generation models have shown promising progress but often exhibit geometric distortions and visual artifacts on portrait videos due to scale-ambiguous camera representations or 3D reconstruction errors. To overcome these limitations, we propose a face-tailored scale-aware representation for camera transformations that provides deterministic conditioning without relying on 3D priors. We train a video generation model on both multi-view studio captures and in-the-wild monocular videos, and introduce two camera-control data generation strategies: synthetic camera motion and multi-shot stitching, to exploit stationary training cameras while generalizing to dynamic, continuous camera trajectories at inference time. Experiments on Ava-256 dataset and diverse in-the-wild videos demonstrate that FaceCam achieves superior performance in camera controllability, visual quality, identity and motion preservation.