Image coding method and device, and decoding method and device based on super-resolution technology

Abstract

The invention discloses an image coding method, an image coding device, an image decoding method and an image decoding device based on a super-resolution technology. The image coding device is positioned at a sending end of an image, and comprises a downsampling module used for performing downsampling on the original image; a first compression module used for compressing the downsampled image forthe first time; a neural network used for performing super-resolution reconstruction on the image that is compressed for the first time to acquire the image that is reconstructed for the first time; afirst addition module used for subtracting the image that is reconstructed for the first time from the original image to acquire a first residual image; a second compression module used for compressing the first residual image for the second time; and a sending module used for jointly sending the compressed first residual image and the image that is compressed for the first time to a receiving end of the image. According to the methods and devices provided by the invention, the code rate is greatly reduced, and meanwhile, the quality of the reconstructed image also can be well enhanced by theapplication of the deep learning technology.

Description

technical field [0001] The present invention relates to an image encoding method and device based on super-resolution technology, and a decoding method and device. Background technique [0002] An image is an approximate and vivid representation of an objective object, and it contains a great deal of relevant information about the object. Statistics show that roughly three-quarters of the information a person obtains comes from vision. It can be said that images are an important source of information for people. Especially in recent years, the rapid development of Internet technology, especially mobile Internet technology, has brought subversive changes and innovations in fields closely related to people's lives, including entertainment and education. In order to deliver a better user experience, an endless stream of various applications are striving to visualize all results to satisfy people's visual experience, including live broadcast, social, media and other fields. I...

AI Technical Summary

Problems solved by technology

However, there is no method disclosed in the prior art for super-resolution reconstruction for image compression

[0008] Traditional image coding is mainly to perform block transformation, quantization, entropy coding, etc. on the image. These methods perform various operations on the same resolution dimension as the original image, which leads to the inability to further reduce the code rate, or in other words, the code rate cannot be further reduced. When the rate is low, the decoded image quality is very poor

Images