Video high dynamic range inverse tone mapping model construction and mapping method and device

Abstract

The invention provides a video high dynamic range inverse tone mapping model construction method, which comprises the following steps of: cutting an original high dynamic range video into a pluralityof high dynamic range videos, converting the high dynamic range videos into standard dynamic range videos, and forming a supervised data set by the standard dynamic range videos and the high dynamic range videos to serve as a subsequent training data set; establishing a video generation network based on a three-dimensional convolutional neural network and skip connection; and establishing a targetloss function integrated by spatial features, time domain features, intrinsic features and perception features for the video generation network, and continuously training and optimizing by adopting the training data set to obtain a final network model. The invention also provides a corresponding construction device and a video high dynamic range inverse tone mapping method. According to the method, the problem of video flicker is solved, and the spatial characteristics, intrinsic characteristics and time domain characteristics of the high-dynamic-range video are considered, so that the inverse tone mapping of the high-dynamic-range video is better realized.

Description

technical field [0001] The present invention relates to a method in the technical field of video processing, in particular to a method and device for constructing a video high dynamic range inverse tone mapping model, and a method for mapping using the constructed model. Background technique [0002] In today's TV display and shooting technology field, high dynamic range (HDR) is undoubtedly a major trend, and ultra-high-definition television (UHD TV) standards also incorporate high dynamic range technology into it. High dynamic range technology enhances the viewing experience of images and videos in terms of both brightness and color. Under the effect of high dynamic range, the global and local contrast of images and videos is greatly improved compared with traditional images and videos, and the details in bright and dark areas can also be improved. At the same time, the color range of the picture will also be expanded, from the widely used standard color gamut BT.709 stan...

AI Technical Summary

Problems solved by technology

[0003] The existing learning-based image inverse tone mapping method will produce flickering phenomenon when applied to the video, which greatly affects the viewing experience

[0004] The invention patent previously applied by the applicant: high dynamic range inverse tone mapping method and system based on generative confrontation network, application number: 201810299749.9, improved the existing

Images