|
1
|
Yu X, Zhang H, Zhao Z, Fan X, Hu S, Li Z, Chen W, Li D, Shi S, Xiong W, Gao H. On the use of deep learning for computer-generated holography. iScience 2025; 28:112507. [PMID: 40491959 PMCID: PMC12146661 DOI: 10.1016/j.isci.2025.112507] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/11/2025] Open
Abstract
The research disciplines of computer-generated holography (CGH) and machine learning have evolved in parallel for decades and experienced booming growth due to breakthroughs in mathematical optimization and computing hardware. Over the past few years, deep learning has been applied to CGH and achieved remarkable success, accustoming a great step toward high-quality and real-time holographic display. This review introduces the fundamental concepts of CGH and deep learning, examines the development of deep-learning-based computer-generated holography (DLCGH), and explores cutting-edge research frontiers including data-driven models, physics-driven models, and jointly optimized models. Finally, we summarize with an outlook on the challenges and prospects of DLCGH.
Collapse
Affiliation(s)
- Xuan Yu
- Wuhan National Laboratory for Optoelectronics and School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
| | - Haomiao Zhang
- Zhejiang University, Hangzhou, Zhejiang 310027, China
- School of Engineering, Westlake University, Hangzhou, Zhejiang 310030, China
| | - Zhe Zhao
- Wuhan National Laboratory for Optoelectronics and School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
| | - Xuhao Fan
- Wuhan National Laboratory for Optoelectronics and School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
| | - Shaodong Hu
- Wuhan National Laboratory for Optoelectronics and School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
| | - Zongjing Li
- Wuhan National Laboratory for Optoelectronics and School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
| | - Wenbin Chen
- Wuhan National Laboratory for Optoelectronics and School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
| | - Daqian Li
- Wuhan National Laboratory for Optoelectronics and School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
| | - Shaoxi Shi
- Wuhan National Laboratory for Optoelectronics and School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
| | - Wei Xiong
- Wuhan National Laboratory for Optoelectronics and School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
- Optics Valley Laboratory, Wuhan, Hubei 430074, China
| | - Hui Gao
- Wuhan National Laboratory for Optoelectronics and School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
- Optics Valley Laboratory, Wuhan, Hubei 430074, China
| |
Collapse
|
|
2
|
Zhu R, Chen L, Zhang H. Computer holography using deep neural network with Fourier basis. OPTICS LETTERS 2023; 48:2333-2336. [PMID: 37126267 DOI: 10.1364/ol.486255] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/03/2023]
Abstract
The use of a deep neural network is a promising technique for rapid hologram generation, where a suitable training dataset is vital for the reconstruct quality as well as the generalization of the model. In this Letter, we propose a deep neural network for phase hologram generation with a physics-informed training strategy based on Fourier basis functions, leading to orthonormal representations of the spatial signals. The spatial frequency characteristics of the reconstructed diffraction fields can be regulated by recombining the Fourier basis functions in the frequency domain. Numerical and optical results demonstrate that the proposed method can effectively improve the generalization of the model with high-quality reconstructions.
Collapse
|