The present disclosure discloses a video processing method and apparatus, which belong to the field of data processing technologies. The method includes: acquiring at least one three-dimensional image, and obtaining a to-be-processed video; parsing the to-be-processed video, to obtain at least two video images; fusing each three-dimensional image with each video image separately, to obtain fused video images; and synthesizing the fused video images into a video, to obtain a processed video. The present disclosure separately fuses each acquired three-dimensional image with each video image obtained by parsing an acquired to-be-processed video, and synthesizes fused video images into a video, to obtain a processed video, which implements adding a three-dimensional image to a video, and enables a processed video to display a three-dimensional image, thereby expanding an application range of video processing, and enriching display effects of the processed video.