Video super-division method and device

The embodiment of the invention provides a video super-division method and device, and relates to the technical field of video processing. The method comprises the following steps: acquiring an original video frame of a to-be-hyper-divided video; according to the pixel value of each pixel point in the original video frame and a preset mapping relation, obtaining the pixel value of each pixel point in a super-division video frame corresponding to the original video frame; the preset mapping relation is a mapping relation generated according to pixel values of pixel points in an input video frame and pixel values of pixel points in an output video frame of a video super-division network model, and the video super-division network model is a model obtained by training a preset machine learning model based on a model training sample; and generating the super-division video frame according to the pixel value of each pixel point in the super-division video frame. The embodiment of the invention is used for performi