Video super-resolution based on enhanced deep feature extraction and residual up-down sampling blocks

Abstract

The invention discloses a video super-resolution method based on enhanced deep feature extraction and residual upper and lower sampling blocks. The method mainly comprises the following steps that a video super-resolution convolutional neural network model based on enhanced deep feature extraction and residual upper and lower sampling blocks is designed and built, and the network is composed of a shallow feature extraction part, a deep feature extraction part, a recursive feature fusion part and a reconstruction part; constructing a training sample pair in the video data set, and training parameters of the constructed convolutional neural network model until the network converges; and inputting a continuous video frame sequence into the trained network model to obtain a super-resolution reconstruction result. According to the method, a low-resolution video can be reconstructed into a high-quality high-resolution video, and the method is an effective video super-resolution reconstruction method.

Description

technical field [0001] The invention relates to image super-resolution reconstruction technology, in particular to a video super-resolution method based on enhanced deep feature extraction and residual up-down sampling blocks, belonging to the field of image processing. Background technique [0002] The goal of super-resolution is to recover high-resolution images or videos from observed low-resolution images or videos. It is widely used in some fields that require high image or video resolution and details, such as medical imaging, remote sensing imaging and satellite detection. In recent years, with the advancement of display technology, a new generation of ultra-high-definition TVs with 4K (3840×2160) and 8K (7680×4320) resolutions has a broad market space, but content matching such high resolutions is still scarce. Thus, video super-resolution is becoming more and more important. Convolutional neural networks have made remarkable progress in the field of video super-re...

AI Technical Summary

Problems solved by technology

However, the existing convolutional neural network-based video super-resolution methods still have room for further improvement in terms of network structure and reconstruction quality.

Images