Method for constructing cost function in compressed video super resolution reconstruction

Abstract

The invention discloses a method for constructing cost function by a compressed video super resolution reconstruction method; in the method, firstly, dividing MAP reconstruction cost function into three parts: a reconstruction error term, a regular constraint term containing distribution parameters of coefficient before quantification and a general constraint term; secondly, reckoning a precise quantification noise model; then, establishing a high resolution image reconstruction error item; afterwards, calculating DCT distribution parameter variance before quantification of low resolution image obtained from high resolution image degradation, minimizing the difference with the original distribution parameter variance, establishing the regular constraint term containing frequency domain coefficient distribution parameters; finally, constructing a reconstruction cost function containing double domains and double variants by the three items. The invention introduces frequency domain distribution coefficient into the calculation of the quantification noise model, so that the calculated quantification noise model is more precise, the cost function constructed based on the quantification noise degradation model is more precise, and the construction quality of compressed video supper solution is improved.

Description

technical field [0001] The invention relates to a method for constructing a cost function, in particular to a method for constructing a cost function by a compressed video super-resolution reconstruction method, which belongs to the field of video image processing. Background technique [0002] Super-resolution reconstruction technology is based on existing imaging equipment and imaging conditions, using single-frame or multi-frame discrete images with poor quality and low resolution, or multiple groups of video sequences to reconstruct images with better quality and higher resolution. High discrete image or video data. Since most of the current videos are compressed, the quantization noise generated by compression is the main reason for the degradation compared to uncompressed videos. Therefore, it is of great significance to construct a cost function that includes an accurate quantization noise model for super-resolution reconstruction of compressed video. [0003] In th...

AI Technical Summary

Problems solved by technology

However, this method does not consider the large estimation error of the high-resolution image during the reconstruction process, which will affect the coefficients before quantization, so it is still difficult to accurately model the compressed video super-resolution reconstruction process.

Images