Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Depth Perception and Spatial Vision

Depth Perception and Spatial Vision

Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

The Interaction Between Insulin Resistance and Neuroinflammation in the Brain and Its Impact on Diabetic Encephalopathy.

Biology·2026

Same author

In Situ Correlation of Dealloying and Oxygen Reduction Activity in Single Au@Ag Nanoparticles.

Nano letters·2026

Same author

Targeted α-synuclein mRNA degradation by PMO-based RNA-degrading chimeras.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

Egg white protein foams: formation and stabilization mechanisms, modification strategies, and applications from foods to functional materials.

Food research international (Ottawa, Ont.)·2026

Same author

Robotic-assisted versus laparoscopic esophageal hiatal hernia and anti-reflux surgery: A comprehensive systematic review and meta-analysis.

Hernia : the journal of hernias and abdominal wall surgery·2026

Same author

Dysbiosis of oral bacteriome and mycobiome associated with the severity of heart failure.

BMC oral health·2026

Search research articles

Related Experiment Video

Updated: Jun 4, 2025

Recording Ultra-Realistic Full-Color Analog Holograms for Use in a Moving Hologram Display

Recording Ultra-Realistic Full-Color Analog Holograms for Use in a Moving Hologram Display

Published on: January 14, 2020

Generation of Multiple-Depth 3D Computer-Generated Holograms from 2D-Image-Datasets Trained CNN.

Xingpeng Yan¹, Jiaqi Li¹, Yanan Zhang¹

¹Department of Information Communication, Army Academy of Armored Forces, Beijing, 100072, China.

Advanced Science (Weinheim, Baden-Wurttemberg, Germany)

|January 1, 2025

Summary

This study introduces a new method for creating computer-generated holograms (CGHs) using 2D images and convolutional neural networks (CNNs). This approach enhances hologram quality and generation speed, overcoming limitations of traditional 3D datasets.

Keywords:

CNN computer‐generated hologram virtual depth datasets

More Related Videos

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

Published on: December 3, 2013

Related Experiment Videos

Last Updated: Jun 4, 2025

Recording Ultra-Realistic Full-Color Analog Holograms for Use in a Moving Hologram Display

Recording Ultra-Realistic Full-Color Analog Holograms for Use in a Moving Hologram Display

Published on: January 14, 2020

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

Published on: December 3, 2013

Area of Science:

Optics and Photonics
Computer Vision
Machine Learning

Background:

Learning-based methods for computer-generated holograms (CGHs) offer high quality and speed.
Limited generalization of CGH models due to data homogenization and difficulty in obtaining 3D datasets.

Purpose of the Study:

To develop a novel approach for training 3D encoding models using 2D image datasets.
To improve the generalization ability of CGH models.

Main Methods:

Utilized convolutional neural networks (CNNs) trained on 2D image datasets to generate virtual depth (VD) images.
Employed the angular spectrum method (ASM) for layer-by-layer diffraction field calculation.
Developed a fully convolutional neural network for phase-only encoding, trained on the DIV2K-VD dataset.

Main Results:

Successfully generated a 4K phase-only hologram in 0.061 seconds.
Achieved high-quality holograms with an average PSNR of 34.7 dB and SSIM of 0.836.
Demonstrated significant improvements in quality, efficiency, and speed compared to traditional methods.

Conclusions:

The proposed CNN-based approach effectively generates high-quality CGHs from 2D data.
This method offers a practical and efficient solution for hologram generation, overcoming dataset limitations.