Data processing method and data processing device

Abstract

The embodiment of the invention discloses a data processing method, which is applied to the field of artificial intelligence, and particularly relates to an image processing technology, and comprisesthe steps of obtaining a frame sequence, frames in the frame sequence having a first resolution; determining at least two frame groups from the frame sequence, each frame group comprising a first target frame and at least two adjacent frames of the first target frame, the first target frame being any frame in the frame sequence, and the adjacent frames being frames other than the first target frame in the frame sequence; determining the feature of each frame group in the at least two frame groups through a three-dimensional convolutional neural network, wherein the size of a convolution kernelin the three-dimensional convolutional neural network in the time dimension is positively correlated with the number of frames in the frame groups; fusing the features of each frame group in the at least two frame groups to determine detail features of the first target frame; and obtaining a first target frame with a second resolution according to the detail features and the first target frame, the second resolution being greater than the first resolution.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to a data processing method and a data processing device. Background technique [0002] Super-resolution (SR), referred to as super-resolution, refers to the technology of reconstructing corresponding high-resolution images from low-resolution images. By upsampling the low-resolution image and filling the details with the help of image prior knowledge and other means, the corresponding high-resolution image is generated. Super-resolution technology has important application value in the fields of high-definition television, monitoring equipment, satellite images and medical imaging. [0003] Video super resolution (Video super resolution, VSR), referred to as video super resolution, is to generate a corresponding high-resolution video from a low-resolution video. A core operation that distinguishes video super resolution from image super resolution is motion ...

AI Technical Summary

Problems solved by technology

[0004] When the existing technology uses 3D convolutional neural network for motion compensation, it is limited by the size of the convolution kernel, and each slide processes 3 frames. Taking the input frame sequence of 7 frames and the 4th frame as the target frame as an example, the volume When the accumulation kernel slides to the 1st, 2nd, and 3rd frames, due to the lack of guidance information of the target frame, the feature extraction will be blind and the feature extraction efficiency will be low

Images