HoloSR: deep learning-based super-resolution for real-time high-resolution computer-generated holograms
Siwoo Lee, Seung‐Woo Nam, Juhyun Lee, Yoonchan Jeong, Byoungho Lee
Abstract
This study presents HoloSR, a novel deep learning-based super-resolution approach designed to produce high-resolution computer-generated holograms from low-resolution RGBD images, enabling the real-time production of realistic three-dimensional images. The HoloSR combines the enhanced deep super-resolution network with resize and convolution layers, facilitating the direct generation of high-resolution computer-generated holograms without requiring additional interpolation. Various upscaling scales, extending up to ×4, are evaluated to assess the performance of our method. Quantitative metrics such as structural similarity and peak signal-to-noise ratio are employed to measure the quality of the reconstructed images. Our simulation and experimental results demonstrate that HoloSR successfully achieves super-resolution by generating high-resolution holograms from low-resolution RGBD inputs with supervised and unsupervised learning.