We propose a deep-learning-based approach to producing computer-generated holograms (CGHs) of real-world scenes. We design an end-to-end convolutional neural network (the Stereo-to-Hologram Network, SHNet) framework that takes a stereo image pair as input and efficiently synthesizes a monochromatic 3D complex hologram as output. The network is able to rapidly and straightforwardly calculate CGHs from the directly recorded images of real-world scenes, eliminating the need for time-consuming intermediate depth recovery and diffraction-based computations. We demonstrate the 3D reconstructions with clear depth cues obtained from the SHNet-based CGHs by both numerical simulations and optical holographic virtual reality display experiments.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1364/OL.453580 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Grids designed for tomography: Stereovision transmission electron microscopy makes it easy to determine the winding handedness of helical nanocoils.
Micron
January 2025
Health and Medical Research Institute, Department of Life Science and Biotechnology, National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba Central-6, 1-1-1 Higashi, Tsukuba, Ibaraki 305-8566, Japan. Electronic address:
Determining the handedness of helical nanocoils using transmission electron microscopy (TEM) has traditionally been challenging due to the deep depth of field and transmission nature of TEM, complementary techniques are considered necessary and have been practiced such as low angle rotary shadowing, scanning electron microscopy (SEM), or atomic force microscopy (AFM). These methods require customized sample preparation, making direct comparison difficult. Inspired by the need to identify the helical winding direction from TEM images alone, we developed a specialized tomography grid to capture stereo-pair images, enabling stereopsis.
View Article and Find Full Text PDFThe effect of arm positions used during radiography on spinal alignment parameters assessed by 3D ultrasound imaging in adolescents with and volunteers without idiopathic scoliosis.
Eur Spine J
January 2025
Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada.
Purpose: Clinicians monitor scoliosis progression using multiple radiographs during growth. During imaging, arms must be elevated to visualize vertebrae, possibly affecting sagittal alignment. This study aimed to determine the arm position that best represents habitual standing (and possibly allowing hand-based skeletal maturity assessment) to obtain frontal and lateral stereo-radiographs as measured using frontal, sagittal, and transverse angles.
View Article and Find Full Text PDFResidual Vision Transformer and Adaptive Fusion Autoencoders for Monocular Depth Estimation.
Sensors (Basel)
December 2024
Institute of Computer and Communication Engineering, Department of Electrical Engineering, National Cheng Kung University, Tainan 701, Taiwan.
Precision depth estimation plays a key role in many applications, including 3D scene reconstruction, virtual reality, autonomous driving and human-computer interaction. Through recent advancements in deep learning technologies, monocular depth estimation, with its simplicity, has surpassed the traditional stereo camera systems, bringing new possibilities in 3D sensing. In this paper, by using a single camera, we propose an end-to-end supervised monocular depth estimation autoencoder, which contains an encoder with a structure with a mixed convolution neural network and vision transformers and an effective adaptive fusion decoder to obtain high-precision depth maps.
View Article and Find Full Text PDFReliable Disparity Estimation Using Multiocular Vision with Adjustable Baseline.
Sensors (Basel)
December 2024
Institute for Computer Research, University of Alicante, P.O. Box 99, 03080 Alicante, Spain.
Article Synopsis
- Accurate 3D information estimation from images is crucial for computer vision, and while binocular stereo vision is a common approach, it faces challenges with baseline distance affecting reliability.
- This research proposes a new method that progressively increases the baseline in multiocular vision, introducing a rectification technique that significantly reduces distortion errors in the images.
- The method enhances disparity estimation accuracy by 20% for multiocular images and demonstrates superior performance through extensive evaluations against existing methods.
Fusion of FDG and FMZ PET Reduces False Positive in Predicting Epileptogenic Zone.
AJNR Am J Neuroradiol
January 2025
From the School of Biomedical Engineering (B.C., H.H., J.L., S.Y., Y.C., J.L.), Shanghai Jiao Tong University, Shanghai, China; Department of Neurosurgery (S.J., J.H., L.C.), and PET Center (W.B.), Huashan Hospital, Fudan University, Shanghai, China.
Background And Purpose: Epilepsy, a globally prevalent neurological disorder, necessitates precise identification of the epileptogenic zone (EZ) for effective surgical management. While the individual utilities of FDG PET and FMZ PET have been demonstrated, their combined efficacy in localizing the epileptogenic zone remains underexplored. We aim to improve the non-invasive prediction of epileptogenic zone (EZ) in temporal lobe epilepsy (TLE) by combining FDG PET and FMZ PET with statistical feature extraction and machine learning.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!