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

You might also read

Related Articles

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

Sort by

Same author

Probing Scalar-Neutrino and Scalar-Dark-Matter Interactions with PandaX-4T.

Physical review letters·2026

Same author

MOF glass-based membranes: a promising platform for advanced separation.

Materials horizons·2026

Same author

Photocatalytic Cascade Nitrogen Fixation for Selective Purification of Methane-Rich Coal-Bed Gas Over a Bimetallic MOF.

Angewandte Chemie (International ed. in English)·2026

Same author

Enhancement of genetic potential for soil carbon and nitrogen cycling by organic fertilizer substitution improves the ecological environment for licorice cultivation.

Frontiers in microbiology·2026

Same author

Precise ^{136}Xe Double Beta Decay Measurement in PandaX-4T with Implications on the Nuclear Matrix Elements and Majorons.

Physical review letters·2026

Same author

The B7 family subgroup reflects tumor cell heterogeneity and patient post-operative prognosis in gallbladder cancer.

Biology direct·2026

Search research articles

Related Experiment Video

Updated: Jul 11, 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

Real-time 4K computer-generated hologram based on encoding conventional neural network with learned layered phase.

Chongli Zhong¹, Xinzhu Sang², Binbin Yan³

¹State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, 100876, China.

Scientific Reports

|November 8, 2023

Summary

A novel neural network efficiently generates 4K computer-generated holograms (CGH) for 3D scenes. This method significantly reduces computational load, enabling real-time holographic display applications.

More Related Videos

Evaluation and Manipulation of Neural Activity Using Two-Photon Holographic Microscopy

Evaluation and Manipulation of Neural Activity Using Two-Photon Holographic Microscopy

Published on: September 16, 2022

Shaping the Amplitude and Phase of Laser Beams by Using a Phase-only Spatial Light Modulator

Shaping the Amplitude and Phase of Laser Beams by Using a Phase-only Spatial Light Modulator

Published on: January 28, 2019

Related Experiment Videos

Last Updated: Jul 11, 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

Evaluation and Manipulation of Neural Activity Using Two-Photon Holographic Microscopy

Evaluation and Manipulation of Neural Activity Using Two-Photon Holographic Microscopy

Published on: September 16, 2022

Shaping the Amplitude and Phase of Laser Beams by Using a Phase-only Spatial Light Modulator

Shaping the Amplitude and Phase of Laser Beams by Using a Phase-only Spatial Light Modulator

Published on: January 28, 2019

Area of Science:

* Optics and Photonics
* Computer Vision and Machine Learning
* Display Technologies

Background:

* Learning-based computer-generated holography (CGH) shows promise for real-time, high-quality holographic displays.
* Generating 4K CGH for 3D scenes in real-time is computationally intensive and challenging.

Purpose of the Study:

* To develop an efficient method for real-time 4K CGH generation for 3D scenes.
* To address the computational challenges in high-resolution holographic display generation.

Main Methods:

* A variant convolutional neural network (CNN) is proposed for CGH encoding.
* The CNN utilizes learned layered initial phases for layered CGH generation, optimizing image quality.
* The network is trained on randomly selected depth layers, featuring a compact 938 parameters.

Main Results:

* Achieved a generation time of 18 ms for 2D 4K CGH, with an additional 12 ms per layer for 3D scenes.
* Demonstrated an average Peak Signal to Noise Ratio (PSNR) above 30 dB within a depth range of 160-210 mm.
* Verified real-time layered 4K CGH generation capabilities.

Conclusions:

* The presented CNN-based approach enables efficient and real-time generation of high-quality 4K CGH for 3D scenes.
* The method overcomes computational limitations, paving the way for advanced holographic display technologies.