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, Andrey S. Svistunov, Rostislav S. Starikov, Anna V. Shifrina, Vladislav G. Rodin, Nikolay N. Evtikhiev, 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":null,"pages":null},"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, Andrey S. Svistunov, Rostislav S. Starikov, Anna V. Shifrina, Vladislav G. Rodin, Nikolay N. Evtikhiev, 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\":null,\"pages\":null},\"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}
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.
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