Image processing method and electronic device

Abstract

Embodiments of this application relate to the field of image processing, and disclose an image processing method and an electronic device, which can accurately and quickly calculate motion vectors of a static mesh and a dynamic mesh separately, thereby reducing computing power overheads for vector calculation, and improving prediction efficiency. A specific solution includes: determining a position of a static mesh of a next frame image based on intermediate rendering variables of at least two completed frame images, where each intermediate rendering variable includes an MVP matrix and depth data of a corresponding frame image; and determining, based on coordinate data of a first model in the at least two completed frame images, a position of the first model in the next frame image. A mesh corresponding to the first model is a dynamic mesh in the image.