Quality evaluation of speckle-noise-contaminated computer-generated holograms by using deep neural network

초록

Computer-generated hologram (CGH) techniques have advanced in the field of display technology, capable of reproducing three-dimensional images. The reconstructed three-dimensional images of the CGHs, however, usually contain speckle noises due to random phase distribution applied in the CGH synthesis. The random distribution of the speckle noise makes the traditional metrics like peak signal-to-noise ratio (PSNR) and structural similarity index map (SSIM), which are generally used in image quality evaluation, become less reliable. In this paper, we propose a novel method to evaluate the speckled CGHs using a deep neural network.

키워드