IMAGE PROCESSING METHOD AND DEVICE

Disclosed are an image processing method and device. The method comprises: acquiring a video code stream, the video code stream comprising a first frame image, a second frame image and a third frame image which are consecutive in timing; decoding the video code stream to obtain a first alignment frame, a second alignment frame, and at least one residual between the first frame image, the second frame image, and the third frame image; generating at least one residual frame according to the at least one residual; and performing super resolution processing on the second frame image according to the at least one residual frame, the first alignment frame and the second alignment frame to obtain a super resolution processed second frame image. The method uses the alignment frames and the residual frame as inputs of a neural network, and as high-frequency information is outputted after the residual frame passes through the neural network, attaching the high-frequency information back to a luminance channel can stren