Smart Machine Vision for Universal Spatial-Mode Reconstruction
Document Type
Article
Publication Date
1-1-2025
Abstract
Structured light beams, in particular, those carrying orbital angular momentum (OAM), have gained a lot of attention due to their potential for enlarging the transmission capabilities of communication systems. However, the use of OAM-carrying light in communications faces two major problems, namely distortions introduced during propagation in disordered media, such as the atmosphere or optical fibers, and the large divergence that high-order OAM modes experience. While the use of nonorthogonal modes may offer a way to circumvent the divergence of high-order OAM fields, artificial intelligence (AI) algorithms have shown promise for solving the mode-distortion issue. Unfortunately, current AI-based algorithms make use of large-amount data-handling protocols that generally lead to large processing time and high power consumption. Here, we show that a low-power, low-cost image sensor can act as an artificial neural network that simultaneously detects and reconstructs distorted OAM-carrying beams. We demonstrate the capabilities of our device by reconstructing (with a 95% efficiency) individual Vortex, Laguerre-Gaussian (LG), and Bessel modes, as well as hybrid (nonorthogonal) coherent superpositions of such modes. Our work provides a potentially useful basis for the development of low-power-consumption, light-based communication devices.
Publication Source (Journal or Book title)
IEEE Transactions on Neural Networks and Learning Systems
First Page
14649
Last Page
14663
Recommended Citation
Huerta-Morales, J., You, C., Magana-Loaiza, O., Dong, S., Leon-Montiel, R., & Quiroz-Juarez, M. (2025). Smart Machine Vision for Universal Spatial-Mode Reconstruction. IEEE Transactions on Neural Networks and Learning Systems, 36 (8), 14649-14663. https://doi.org/10.1109/TNNLS.2025.3530302