Global phase insensitive loss function for deep learning in holographic imaging and projection applications

Zheng, Yijie; Gordon, George

Abstract

Holographic imaging and projection are increasingly used for important applications such as augmented reality, 3D microscopy and imaging through optical fibres. However, there are emerging applications that require control or detection of phase, where deep learning techniques are used as faster alternatives to conventional hologram generation algorithms or phase-retrieval algorithms. Although conventional mean absolute error (MAE) loss function or mean squared error (MSE) can directly compare complex values for absolute control of phase, there is a class of problems whose solutions are degenerate within a global phase factor, but whose relative phase between pixels must be preserved. In such cases, MAE is not suitable because it is sensitive to global phase differences. We therefore develop a ‘global phase insensitive’ loss function that estimates the global phase factor between predicted and target outputs and normalises the predicted output to remove this factor before calculating MAE. As a case study we demonstrate ≤ 0.1% error in the recovery of complex-valued optical fibre transmission matrices via a neural network. This global phase insensitive loss function will offer new opportunities for deep learning-based holographic image reconstruction, 3D holographic projection for augmented reality and coherent imaging through optical fibres.

Citation

Zheng, Y., & Gordon, G. Global phase insensitive loss function for deep learning in holographic imaging and projection applications. Presented at AI and Optical Data Sciences IV, San Francisco, United States

• Presentation Conference Type: Conference Paper (published)
• Conference Name: AI and Optical Data Sciences IV
• Acceptance Date: Jan 25, 2023
• Online Publication Date: Mar 15, 2023
• Publication Date: Feb 3, 2023
• Deposit Date: Mar 31, 2023
• Publicly Available Date: Apr 26, 2023
• Journal: Proceedings of SPIE
• Print ISSN: 0277-786X
• Electronic ISSN: 1996-756X
• Publisher: Society of Photo-optical Instrumentation Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 12438
• Article Number: 11243811
• ISBN: 9781510659810
• DOI: https://doi.org/10.1117/12.2648040
• Public URL: https://nottingham-repository.worktribe.com/output/19009066
• Publisher URL: https://www.spiedigitallibrary.org/conference-proceedings-of-spie/12438/2648040/Global-phase-insensitive-loss-function-for-deep-learning-in-holographic/10.1117/12.2648040.short?SSO=1