A single-frame image super-resolution processing method based on diffusion model

Abstract

The invention discloses a single-frame image super-resolution processing method based on a diffusion model. Methods The diffusion process and conditional noise predictor of the super-resolution diffusion model were established; the high and low resolution image data sets were input into the conditional noise predictor of the super-resolution diffusion model, and the conditional noise predictor was trained by the diffusion process of the super-resolution diffusion model, and the obtained The pre-trained conditional noise predictor; the low-resolution image to be processed is input into the inverse process of the super-resolution diffusion model, and the residual prediction image is obtained; the residual prediction image is added to the low-resolution image after the upsampling operation to obtain the prediction super-resolution images. The invention generates multiple super-resolution images with consistent features for the same low-resolution image, each super-resolution image has rich texture and naturalness, avoids the problem of over-smoothing and mode collapse, and improves the performance with less time overhead. Rebuild performance.

Description

technical field [0001] The invention belongs to an image processing method in the fields of image processing technology, computer vision and deep learning, and in particular relates to a single-frame image super-resolution processing method based on a diffusion model in the technical field of image super-resolution. Background technique [0002] The single-frame image super-resolution task has a wide range of applications in the field of computer vision, such as object recognition, multimedia technology, aerospace imaging, etc. The single-frame image super-resolution task aims to recover high-resolution images from low-resolution images, which is an ill-posed problem because multiple high-resolution images can degenerate into the same low-resolution image. [0003] In order to establish the mapping between high-resolution images and low-resolution images, many neural network-based methods have emerged in recent years, and these methods can be divided into three main types: P...

AI Technical Summary

Problems solved by technology

However, the PSNR-oriented feedforward super-resolution neural network method obtains the average of multiple super-resolution potential solutions, resulting in a super-resolution image that is too smooth; the method based on GAN is prone to "mode collapse", resulting in the generation of super-resolution images. Close to the same solution; flow-based methods require huge model parameters and computational overhead

How to generate multiple high-quality high-resolution images consistent with the same low-resolution image while avoiding large computational overhead is not solved and realized in the prior art

Images