3D-CGH-Net:通过深度学习生成可定制的三维全息图

IF 3.5 2区 工程技术 Q2 OPTICS
Dmitry A. Rymov, Andrey S. Svistunov, Rostislav S. Starikov, Anna V. Shifrina, Vladislav G. Rodin, Nikolay N. Evtikhiev, Pavel A. Cheremkhin
{"title":"3D-CGH-Net:通过深度学习生成可定制的三维全息图","authors":"Dmitry A. Rymov,&nbsp;Andrey S. Svistunov,&nbsp;Rostislav S. Starikov,&nbsp;Anna V. Shifrina,&nbsp;Vladislav G. Rodin,&nbsp;Nikolay N. Evtikhiev,&nbsp;Pavel A. Cheremkhin","doi":"10.1016/j.optlaseng.2024.108645","DOIUrl":null,"url":null,"abstract":"<div><div>Computer generated holograms can create arbitrary light distributions through computation of light propagation. 3D-computer-generated-hologram generation requires significant computation time, especially so for 3D-computer-generated-holograms where it is important to calculate the interactions between different planes on top of the planes themselves. In this paper we propose a neural-network-based method for 3D-computer-generated-hologram generation in order to improve the hologram computation speed. The trained model can be used to generate holograms with arbitrary light propagation parameters. The neural network was numerically and optically tested against the GS algorithm using 3D-computer-generated-holograms with resolution up to 1024×1024 pixels. 3D-holograms with 16 object planes were generated, which is, to our knowledge, the highest number currently achieved with a neural-network-based-method. The experiments show that proposed model can create holograms significantly faster than some conventional algorithms and, overall, results better-quality images. The trained network can also be used using different propagation parameters, such as wavelength and focal distance.</div></div>","PeriodicalId":49719,"journal":{"name":"Optics and Lasers in Engineering","volume":"184 ","pages":"Article 108645"},"PeriodicalIF":3.5000,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"3D-CGH-Net: Customizable 3D-hologram generation via deep learning\",\"authors\":\"Dmitry A. Rymov,&nbsp;Andrey S. Svistunov,&nbsp;Rostislav S. Starikov,&nbsp;Anna V. Shifrina,&nbsp;Vladislav G. Rodin,&nbsp;Nikolay N. Evtikhiev,&nbsp;Pavel A. Cheremkhin\",\"doi\":\"10.1016/j.optlaseng.2024.108645\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Computer generated holograms can create arbitrary light distributions through computation of light propagation. 3D-computer-generated-hologram generation requires significant computation time, especially so for 3D-computer-generated-holograms where it is important to calculate the interactions between different planes on top of the planes themselves. In this paper we propose a neural-network-based method for 3D-computer-generated-hologram generation in order to improve the hologram computation speed. The trained model can be used to generate holograms with arbitrary light propagation parameters. The neural network was numerically and optically tested against the GS algorithm using 3D-computer-generated-holograms with resolution up to 1024×1024 pixels. 3D-holograms with 16 object planes were generated, which is, to our knowledge, the highest number currently achieved with a neural-network-based-method. The experiments show that proposed model can create holograms significantly faster than some conventional algorithms and, overall, results better-quality images. The trained network can also be used using different propagation parameters, such as wavelength and focal distance.</div></div>\",\"PeriodicalId\":49719,\"journal\":{\"name\":\"Optics and Lasers in Engineering\",\"volume\":\"184 \",\"pages\":\"Article 108645\"},\"PeriodicalIF\":3.5000,\"publicationDate\":\"2024-10-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Optics and Lasers in Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0143816624006237\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"OPTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Optics and Lasers in Engineering","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0143816624006237","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"OPTICS","Score":null,"Total":0}
引用次数: 0

摘要

计算机生成的全息图可以通过计算光的传播来创建任意的光分布。三维计算机生成的全息图需要大量的计算时间,尤其是对于三维计算机生成的全息图来说,在平面本身的基础上计算不同平面之间的相互作用非常重要。本文提出了一种基于神经网络的三维计算机生成全息图方法,以提高全息图的计算速度。训练好的模型可用于生成具有任意光传播参数的全息图。使用分辨率高达 1024×1024 像素的三维计算机生成全息图,对神经网络与 GS 算法进行了数值和光学测试。生成的三维全息图有 16 个对象平面,据我们所知,这是目前基于神经网络方法生成的最高数量。实验结果表明,所提出的模型生成全息图的速度明显快于一些传统算法,而且总体上能生成质量更好的图像。经过训练的网络还可以使用不同的传播参数,如波长和焦距。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
3D-CGH-Net: Customizable 3D-hologram generation via deep learning
Computer generated holograms can create arbitrary light distributions through computation of light propagation. 3D-computer-generated-hologram generation requires significant computation time, especially so for 3D-computer-generated-holograms where it is important to calculate the interactions between different planes on top of the planes themselves. In this paper we propose a neural-network-based method for 3D-computer-generated-hologram generation in order to improve the hologram computation speed. The trained model can be used to generate holograms with arbitrary light propagation parameters. The neural network was numerically and optically tested against the GS algorithm using 3D-computer-generated-holograms with resolution up to 1024×1024 pixels. 3D-holograms with 16 object planes were generated, which is, to our knowledge, the highest number currently achieved with a neural-network-based-method. The experiments show that proposed model can create holograms significantly faster than some conventional algorithms and, overall, results better-quality images. The trained network can also be used using different propagation parameters, such as wavelength and focal distance.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Optics and Lasers in Engineering
Optics and Lasers in Engineering 工程技术-光学
CiteScore
8.90
自引率
8.70%
发文量
384
审稿时长
42 days
期刊介绍: Optics and Lasers in Engineering aims at providing an international forum for the interchange of information on the development of optical techniques and laser technology in engineering. Emphasis is placed on contributions targeted at the practical use of methods and devices, the development and enhancement of solutions and new theoretical concepts for experimental methods. Optics and Lasers in Engineering reflects the main areas in which optical methods are being used and developed for an engineering environment. Manuscripts should offer clear evidence of novelty and significance. Papers focusing on parameter optimization or computational issues are not suitable. Similarly, papers focussed on an application rather than the optical method fall outside the journal''s scope. The scope of the journal is defined to include the following: -Optical Metrology- Optical Methods for 3D visualization and virtual engineering- Optical Techniques for Microsystems- Imaging, Microscopy and Adaptive Optics- Computational Imaging- Laser methods in manufacturing- Integrated optical and photonic sensors- Optics and Photonics in Life Science- Hyperspectral and spectroscopic methods- Infrared and Terahertz techniques
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信