We propose a high-quality, three-dimensional display system based on a simplified light field image acquisition method, and a custom-trained full-connected deep neural network is proposed. The ultimate goal of the proposed system is to acquire and reconstruct the light field images with possibly the most elevated quality from the real-world objects in a general environment. A simplified light field image acquisition method acquires the three-dimensional information of natural objects in a simple way, with high-resolution/high-quality like multicamera-based methods. We trained a full-connected deep neural network model to output desired viewpoints of the object with the same quality. The custom-trained instant neural graphics primitives model with hash encoding output the overall desired viewpoints of the object within the acquired viewing angle in the same quality, based on the input perspectives, according to the pixel density of a display device and lens array specifications within the significantly short processing time. Finally, the elemental image array was rendered through the pixel re-arrangement from the entire viewpoints to visualize the entire field-of-view and re-constructed as a high-quality three-dimensional visualization on the integral imaging display. The system was implemented successfully, and the displayed visualizations and corresponding evaluated results confirmed that the proposed system offers a simple and effective way to acquire light field images from real objects with high-resolution and present high-quality three-dimensional visualization on the integral imaging display system.

We present a novel augmented reality (AR) display system utilizing a holographic optical element (HOE)-based approach, featuring seamless switching between three-dimensional (3D) and two-dimensional (2D) modes through a liquid-crystalline microlens array (LC-MLA). The proposed system aims to capture and present comprehensive spatial information on real-world objects. The LC-MLA is customized to suit the purpose of the proposed system, and its functionality seamlessly switches via an electrical polarizer, allowing users to effortlessly toggle between modes by simply pressing a switch button. An integrated control system automates corresponding tasks based on the selected mode. In 2D mode, the captured image is directly displayed, while in 3D mode, an elemental image array (EIA) is generated and reconstructed into a 3D image, through the LC-MLA. To ensure optimal performance for the proposed system, a custom-fabricated LC-MLA, and full-color HOE combiner have been developed. Additionally, we designed and implemented a bespoke integrated control system that synchronizes and interconnects the main devices seamlessly.

Holography is an emerging technology where phase-only spatial light modulator (SLM) is better than amplitude-only SLM because of its enhanced diffraction efficiency and rendering quality. However, phase-only interference pattern reconstruction is an ill-posed inverse problem, difficult to solve by standard supervised neural network approaches. Accurately representing the target input during reconstruction of phase-only hologram (POH) can become challenging given the inherent high spatial frequency of phase data and the complexity of its fringe patterns, expressing the inverse nature of the problem. Therefore, the model may be trained improperly, inducing major compromise in the predicted hologram’s quality. As a result, an unsupervised approach can be effective to resolve such a problem. This paper presents a novel combined U2-net-based computer-generated hologram (CUSNet-CGH) architecture, an end-to-end deep learning model comprising two distinctively designed combined convolution networks that accurately generate 2D POH. The proposed framework contains U2-net which is known for performing unsupervised learning tasks without relying on pre-trained backbones from labeled dataset, making it an ideal approach for conducting unsupervised training. The numerical reconstructions are compared with several other state-of-the-art methods such as holoencoder, holonet and CCNN-CGH to verify the enhanced quality. The average PSNR of the proposed end-to-end approach is as high as ~34 dB with an average SSIM of 0.91, featured by DIV2K dataset, outperforming the state-of-the-art methods analyzed in the paper. Additionally, the time required to reconstruct the predicted output of the proposed model is verified as competitive, challenging the latest benchmarks, thanks to its minimized number of trainable parameters, and ensuring that the model is computationally lightweight. Finally, experiments also demonstrate that the proposed model yields high-quality optical reconstruction.

We propose generated a high-quality 3D model using a deep neural network by acquiring high-resolution 3D data from real-world objects and generated a high-speed and high-quality 3D CGH based on integrated hybrid map layering for use in holographic display.