We present an approach to modeling an image-space prior on scene dynamics.
Our prior is learned from a collection of motion trajectories extracted from
real video sequences containing natural, oscillating motion such as trees,
flowers, candles, and clothes blowing in the wind. Given a single image, our
trained model uses a frequency-coordinated diffusion sampling process to
predict a per-pixel long-term motion representation in the Fourier domain,
which we call a neural stochastic motion texture. This representation can be
converted into dense motion trajectories that span an entire video. Along with
an image-based rendering module, these trajectories can be used for a number of
downstream applications, such as turning still images into seamlessly looping
dynamic videos, or allowing users to realistically interact with objects in
real pictures.

我们提出了一种对场景动态进行图像空间先验建模的方法，该先验是从包含自然振动运动（如树木、花朵、蜡烛和风中的衣物）的真实视频序列中提取的一系列运动轨迹学习得到的。通过一个经过训练的模型，我们使用一种频率协调扩散抽样过程来预测傅里叶域中每个像素长期运动表示，我们称之为神经随机运动纹理。这种表示可以转换为跨越整个视频的密集运动轨迹。结合基于图像的渲染模块，这些轨迹可以用于许多下游应用，例如将静止图像转换为无缝循环的动态视频，或者允许用户在真实图片中与物体进行真实交互。