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.

[1]  Marius Tico,et al.  Image enhancement method via blur and noisy image fusion , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[2]  Chi-Keung Tang,et al.  Deep High Dynamic Range Imaging with Large Foreground Motions , 2017, ECCV.

[3]  Shree K. Nayar,et al.  Determining the Camera Response from Images: What Is Knowable? , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Rynson W. H. Lau,et al.  Image Correction via Deep Reciprocating HDR Transformation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[5]  Yung-Yu Chuang,et al.  Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Subhasis Chaudhuri,et al.  Reconstruction of high contrast images for dynamic scenes , 2011, The Visual Computer.

[7]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[8]  Fahd Bouzaraa,et al.  Learnable Exposure Fusion for Dynamic Scenes , 2018, ArXiv.

[9]  Nima Tajbakhsh,et al.  UNet++: A Nested U-Net Architecture for Medical Image Segmentation , 2018, DLMIA/ML-CDS@MICCAI.

[10]  Thomas Bashford-Rogers,et al.  ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content , 2018, Comput. Graph. Forum.

[11]  Peter J. Burt,et al.  Enhanced image capture through fusion , 1993, 1993 (4th) International Conference on Computer Vision.

[12]  Ravi Ramamoorthi,et al.  Deep high dynamic range imaging of dynamic scenes , 2017, ACM Trans. Graph..

[13]  Greg Ward,et al.  Automatic High-Dynamic Range Image Generation for Dynamic Scenes , 2008, IEEE Computer Graphics and Applications.

[14]  R. Venkatesh Babu,et al.  DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).