Towards Robust and Generalizable Gerchberg Saxton based Physics Inspired Neural Networks for Computer Generated Holography: A Sensitivity Analysis Framework
This work addresses robustness and generalization issues in holographic applications like AR and displays, but it is incremental as it builds on existing GS-PINN methods with a new analysis framework.
The paper tackled the problem of limited generalization and benchmarking in Gerchberg-Saxton-based physics-inspired neural networks for computer-generated holography by developing a sensitivity analysis framework, identifying SLM pixel-resolution as the primary factor affecting performance and showing that free space propagation models outperform Fourier holography for enhanced generalization.
Computer-generated holography (CGH) enables applications in holographic augmented reality (AR), 3D displays, systems neuroscience, and optical trapping. The fundamental challenge in CGH is solving the inverse problem of phase retrieval from intensity measurements. Physics-inspired neural networks (PINNs), especially Gerchberg-Saxton-based PINNs (GS-PINNs), have advanced phase retrieval capabilities. However, their performance strongly depends on forward models (FMs) and their hyperparameters (FMHs), limiting generalization, complicating benchmarking, and hindering hardware optimization. We present a systematic sensitivity analysis framework based on Saltelli's extension of Sobol's method to quantify FMH impacts on GS-PINN performance. Our analysis demonstrates that SLM pixel-resolution is the primary factor affecting neural network sensitivity, followed by pixel-pitch, propagation distance, and wavelength. Free space propagation forward models demonstrate superior neural network performance compared to Fourier holography, providing enhanced parameterization and generalization. We introduce a composite evaluation metric combining performance consistency, generalization capability, and hyperparameter perturbation resilience, establishing a unified benchmarking standard across CGH configurations. Our research connects physics-inspired deep learning theory with practical CGH implementations through concrete guidelines for forward model selection, neural network architecture, and performance evaluation. Our contributions advance the development of robust, interpretable, and generalizable neural networks for diverse holographic applications, supporting evidence-based decisions in CGH research and implementation.