| Title |
Efficient Deep Neural Network for Restoring Image Intensity |
| Authors |
Keunsoo Heo(Keunsoo Heo) ; Yunju Kim(Yunju Kim) ; Changwoo Lee(Changwoo Lee) |
| DOI |
https://doi.org/10.5573/IEIESPC.2019.8.2.121 |
| Keywords |
Deep learning ; Restoration of image intensity ; Companding ; Clipping ; U-net |
| Abstract |
In order to maximize the image quality when using existing image contents in the latest display devices, it is necessary to improve the resolution and intensity of the images. In this paper, we propose an efficient deep neural network to restore the image intensity when there are too few bits per pixel to provide more intensity. We investigate an efficient implementation and training method for U-net to maximize the performance of restoring image intensity. We show that we can significantly improve the perceptual quality of the restored image by using VGG loss as well as MSE loss to train U-net. The perceptual loss of images can be efficiently dealt with by using VGG loss. The convergence of the proposed method is analyzed, and extensive computer simulations show that the proposed method significantly improves the perceptual quality of the restored image. |