End-to-end quality enhancement method and device based on binocular stereo image

Abstract

The embodiment of the invention discloses an end-to-end quality enhancement method and an end-to-end quality enhancement device based on a binocular stereo image. The method comprises the steps of respectively inputting low / high-quality images in the binocular stereo images into a feature extraction network for feature extraction; respectively inputting the obtained shallow feature maps of the low / high-quality images into an information distillation network for information distillation; and then inputting the obtained high-level feature map of the low / high-quality image into an information fusion network for information fusion, finally inputting the obtained fusion feature map into a long short-term memory network to learn the visual difference of the three-dimensional image, and reconstructing to obtain a quality enhanced image of the low-quality image. According to the invention, an end-to-end image quality enhancement algorithm is adopted. High-quality images are used for guiding low-quality image reconstruction. The visual difference of the three-dimensional images is learned through the long-term and short-term memory network based on information fusion. The operation speed can be increased. The error transmission can be avoided. The speed and accuracy of image reconstruction are guaranteed, and the consumption of internal storage and computing resources is reduced.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an end-to-end binocular stereo image-based quality enhancement method and device. Background technique [0002] Quality enhancement of stereoscopic images has become an active research area in recent years with the increase of additional information in disparity. [0003] Since the pioneering work of Super-Resolution Convolutional Neural Network (SRCNN, Super-Resolution Convolutional Neural Network), learning-based methods have been widely adopted to enhance image quality. Currently commonly used stereo image enhancement methods use stereo matching to learn the correspondence between stereo image pairs, and use cost volumes to simulate long-term dependencies in the network. However, due to the large differences between different viewpoints of stereo image pairs, It is quite difficult to learn the accurate correspondence between stereoscopic image pairs. In addi...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the embodiments of the present invention is to provide an end-to-end binocular stereo image-based quality enhancement method and device, which can at least solve the difficulty in learning the accurate relationship between stereo image pairs when performing stereo image quality enhancement in the related art. Correspondence, and problems that require a lot of computing resources and memory consumption

Images