Super-resolution, color gamut expansion and inverse tone mapping combined method and device

Abstract

The invention provides a super-resolution, color gamut expansion and inverse tone mapping combined method and device, and the method comprises the steps: S1, carrying out down-conversion on video frames with high resolution, high color gamut and high dynamic range into video frames with low resolution, low color gamut and standard dynamic range, and forming a training data set and a test data set;S2, designing a convolutional neural network based on local residual learning and global residual learning; S3, continuously training and optimizing the convolutional neural network by using the training data set to obtain a convolutional neural network capable of completing joint super-resolution, color gamut extension and inverse tone mapping; and S4, inputting the low-resolution, low-color-gamut and standard dynamic range video frames in the test data set into the convolutional neural network obtained after training in S3 to obtain high-resolution, high-color-gamut and high-dynamic range video frames. According to the invention, the artifact problem of the existing method is improved, and the subjective and objective quality is improved.

Description

technical field [0001] The present invention relates to a method in the technical field of image processing, in particular to a convolutional neural network-based joint super-resolution, color gamut extension, and inverse tone mapping method and device. Background technique [0002] In recent years, shooting and display technologies have developed rapidly, and a large number of consumer-grade cameras and displays with high resolution, high color gamut, and high dynamic range have appeared on the market. The Recommendation ITU-R BT.2020 standard defines the relevant parameters of ultra-high-definition television, stipulating that its resolution is 3840×2160 or 7680×4320, and the number of quantization bits is 10 bits or 12 bits. The BT.709 standard HDTV resolution is 1920×1080, and the number of coding bits is 8 bits or 10 bits. The color gamut specified by the Recommendation ITU-R BT.2020 standard is larger than that specified by the Recommendation ITU-R BT.709. The Recomm...

AI Technical Summary

Problems solved by technology

[0004] The traditional method only performs one-to-one mapping of pixels, and cannot reconstruct high-frequency information, texture details and rich colors

Some deep learning-based methods that have appeared in recent years have artifact problems, so the subjective quality is not high

Images