Digital cameras with a single sensor use a color filter array (CFA) that captures only one color component in each pixel. Therefore,\nnoise and artifacts will be generated when reconstructing the color image, which reduces the resolution of the image. In this paper,\nwe proposed an image demosaicing method based on generative adversarial network (GAN) to obtain high-quality color images.\nThe proposed network does not need any initial interpolation process in the data preparation phase, which can greatly reduce the\ncomputational complexity.Thegenerator of the GAN is designed using the U-net to directly generate the demosaicing images.The\ndense residual network is used for the discriminator to improve the discriminant ability of the network. We compared the\nproposed method with several interpolation-based algorithms and the DnCNN. Results from the comparative experiments proved\nthat the proposed method can more effectively eliminate the image artifacts and can better recover the color image.
Loading....