Image’s Dynamic Range and Color Gamut Conversion Based on Cycle GAN

Image dynamic range conversion is a hot topic in the field of image processing. This function mainly realizes the transformation of image from low dynamic range to high dynamic range, which makes the details of image brighter and darker more significant and improves the image’s quality. Based on the idea of generative adversarial network, an image transform network is constructed by using cycleGAN. The network can not only transform the dynamic range of image, but also make the image change from one gamut standard to another. In this training, a new dataset is adopted, which includes six kinds of image data based on ITU-R BT.709 gamut and ITU-R BT.2020 gamut. The loss functions of gradient, color and PSNR value are added to the network, and the effectiveness of the algorithm is verified by image evaluation indexes such as HSV spatial color difference and SSIM value.