Video compression using optical streams

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing video data. In one aspect, a method includes receiving a sequence of video frames; generating an optical flow between two sequential frames using a flow prediction network, the two sequential frames including a first frame and a second frame after the first frame; generating, from an optical flow using a first autoencoder neural network: a predicted optical flow between the first frame and the second frame; and warping the reconstruction of the first frame according to the predicted optical flow, and then applying a blurring operation to obtain an initial predicted reconstruction of the second frame. 用于压缩视频数据的方法、系统和装置，包括在计算机存储介质上编码的计算机程序。在一个方面中，一种方法包括：接收视频帧序列；使用流预测网络生成两个顺序帧之间的光流，其中，所述两个顺序帧包括第一帧和在所述第一帧之后的第二帧；使用第一自动编码器神经网络从光流生成：所述第一帧和所述第二帧之间的预测光流；以及根据预测光流扭曲所述第一帧的重构，并且随后应用模糊操作以获得所述第二帧的初始预测重构。