Optical Mode Sorting with a Programmable Diffractive Neural Network
Abstract
Programmable diffractive optical processors are particularly attractive for spatial light manipulation because their optical transformations can be dynamically reconfigured and adapted without modifying the physical hardware. However, their practical performance is often limited by the gap between simulation and experiment caused by optical aberrations, alignment errors, and nonideal phase responses. In this paper, we introduce a hybrid optimization framework that combines high-dimensional numerical design with low-dimensional hardware-in-the-loop calibration, enabling programmable diffractive optical networks to compensate experimentally for mismatch without retraining their underlying optical transformations. We demonstrate a programmable optical diffractive neural network (ODNN) designed by back-propagation to spatially sort six linearly polarized modes supported by a multimode fiber. The experimental distortions are represented using a truncated Zernike basis with only 19 correction coefficients per layer. These coefficients are optimized directly on the physical system using stochastic parallel gradient descent, avoiding re-optimization of the full pixelated phase masks. Experimentally, the proposed calibration yields an SNR improvement of approximately 3.26 dB, and a decrease in amplitude error of 0.04. This separation of high-dimensional optical-function design from low-dimensional physical calibration provides a scalable route towards adaptive and reconfigurable spatial-mode processors for optical router on spatial modes and wavelengths, programmable photonic computer systems and quantum information processing.
Related
- Quantization-Aware Nonlinear Diffractive Neural Network for Robust Optical Image Reconstruction under Fabrication Constraints
- Cascaded Holographic-Diffractive Neural Network with Dual-Polarization Multiplexing for High-Security Optical Encryption
- Diffractive optical-digital neural networks for robust EUV mask phase-defect characterization and classification
- Deep diffractive optical neural networks for detecting skyrmionic topologies of light and their live training
- High-speed optical target feature extractor based on multimode fiber optical neural network
BibTeX
@misc{zhang2026optical,
title = {{Optical Mode Sorting with a Programmable Diffractive Neural Network}},
author = {Qian Zhang and Shiyue Chen and Juergen W Czarske},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.22015},
eprint = {2609.22015},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.22015},
}
RIS
TY - UNPB
TI - Optical Mode Sorting with a Programmable Diffractive Neural Network
AU - Qian Zhang
AU - Shiyue Chen
AU - Juergen W Czarske
PY - 2026
DA - 2026/09/22
PB - arXiv
DO - 10.48550/arxiv.2609.22015
UR - https://arxiv.org/abs/2609.22015
AB - Programmable diffractive optical processors are particularly attractive for spatial light manipulation because their optical transformations can be dynamically reconfigured and adapted without modifying the physical hardware. However, their practical performance is often limited by the gap between simulation and experiment caused by optical aberrations, alignment errors, and nonideal phase responses. In this paper, we introduce a hybrid optimization framework that combines high-dimensional numerical design with low-dimensional hardware-in-the-loop calibration, enabling programmable diffractive optical networks to compensate experimentally for mismatch without retraining their underlying optical transformations. We demonstrate a programmable optical diffractive neural network (ODNN) designed by back-propagation to spatially sort six linearly polarized modes supported by a multimode fiber. The experimental distortions are represented using a truncated Zernike basis with only 19 correction coefficients per layer. These coefficients are optimized directly on the physical system using stochastic parallel gradient descent, avoiding re-optimization of the full pixelated phase masks. Experimentally, the proposed calibration yields an SNR improvement of approximately 3.26 dB, and a decrease in amplitude error of 0.04. This separation of high-dimensional optical-function design from low-dimensional physical calibration provides a scalable route towards adaptive and reconfigurable spatial-mode processors for optical router on spatial modes and wavelengths, programmable photonic computer systems and quantum information processing.
ER -