Geo-Align: 基于度量几何奖励的视频生成对齐

摘要

近年来，相机控制视频生成取得了显著进展。然而，现有视频到视频重渲染方法主要依赖合成数据集的监督微调。目前，同步的多视角真实世界视频数据极度匮乏。因此，现有范式在处理分布外的真实世界视频时，泛化能力往往有限，模型难以精确遵循物理尺度和相机轨迹。为弥补这一差距，我们提出了Geo-Align，这是首个专门针对相机控制视频重渲染设计的强化学习框架。基于预训练模型，我们通过一种尺度感知的感知奖励机制对模型进行优化。具体而言，我们引入了一个度量3D估计器，从生成的视频中提取精确的相机轨迹，并显式惩罚旋转和平移的偏差。此外，我们精心设计了一种基于真实世界条件视频和源自合成数据的目标相机轨迹的数据流程策略，消除了对配对数据的依赖。大量实验表明，Geo-Align在精确相机可控性和视觉保真度方面持续优于现有监督学习基线，证明了我们方法的有效性。

English

Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rely on Supervised Fine-Tuning using synthetic datasets. At present, there is an extreme scarcity of synchronized, multi-view real-world video data. Consequently, the prevailing paradigm often exhibits limited generalization when processing out-of-distribution real-world videos, with models struggling to accurately adhere to physical scales and camera trajectories. To bridge this gap, we propose Geo-Align, the first Reinforcement Learning framework specifically designed for camera-controlled video re-rendering. Built upon a pretrained model, we optimize the model through a scale-aware perceptual reward mechanism. Specifically, we introduce a metric 3D estimator to extract precise camera trajectories from generated videos, explicitly penalizing deviations in rotation and translation. Furthermore, we meticulously designed a data pipeline strategy based on real-world conditioning videos and target camera trajectories derived from synthetic data, eliminating the reliance on paired data. Extensive experiments demonstrate that Geo-Align consistently outperforms existing supervised learning baselines in both precise camera controllability and visual fidelity, indicating the effectiveness of our method.