VIDEO PROCESSING METHOD AND VIDEO PROCESSING APPARATUS

The present disclosure relates to a video processing method and a video processing apparatus. The video processing method comprises: acquiring the current frame image and a first area mask of a video, wherein a first area corresponds to an area that is expected to be removed from the current frame image; on the basis of the current frame image and the first area mask, acquiring a first result image of the current frame image by using an image processing network, wherein the first result image is an image obtained after the first area is removed from the current frame image; acquiring a second result image of a previous frame image of the current frame image of the video, wherein the second result image is an image obtained after the first area is removed from the previous frame image; and fusing the first result image of the current frame image with the second result image of the previous frame image, so as to obtain a final result image of the current frame image. La présente divulgation concerne un procédé