Abstract
Panoramic video generation has attracted growing attention due to its applications in virtual reality and immersive media. However, existing methods lack explicit motion control and struggle to generate scenes with large and complex motions. We propose PanFlow, a novel approach that exploits the spherical nature of panoramas to decouple the highly dynamic camera rotation from the input optical flow condition, enabling more precise control over large and dynamic motions. We further introduce a spherical noise warping strategy to promote loop consistency in motion across panorama boundaries. To support effective training, we curate a large-scale, motion-rich panoramic video dataset with frame-level pose and flow annotations. We also showcase the effectiveness of our method in various applications, including motion transfer and video editing. Extensive experiments demonstrate that PanFlow significantly outperforms prior methods in motion fidelity, visual quality, and temporal coherence. Our code, dataset, and models are available at this https URL.
Abstract (translated)
全景视频生成因其在虚拟现实和沉浸式媒体中的应用而引起了越来越多的关注。然而，现有的方法缺乏明确的运动控制，并且难以生成具有大范围复杂运动场景的内容。我们提出了PanFlow，这是一种新颖的方法，它利用了全景图像的球形特性来将高度动态的相机旋转与输入光流条件分离出来，从而能够对大规模和动态变化进行更精确的控制。此外，我们还引入了一种球面噪声扭曲策略，以促进跨越全景边界时运动的一致性。 为了支持有效的训练，我们整理了一个大型、包含丰富运动信息的全景视频数据集，并提供了逐帧的姿态和光流标注。我们在各种应用中展示了我们的方法的有效性，包括动作转移和视频编辑。大量的实验表明，PanFlow在运动保真度、视觉质量和时间一致性方面都显著优于以前的方法。 我们的代码、数据集和模型可在以下链接获得：[此URL](https://this https URL)（请注意，实际使用时应提供有效的URL）。
URL
https://arxiv.org/abs/2512.00832
