Generative adversarial network for super-resolution imaging through a fiber
arXiv:2201.00601 · doi:10.1103/PhysRevApplied.18.034075
Abstract
A multimode fiber represents the ultimate limit in miniaturization of imaging endoscopes. Here we propose a fiber imaging approach employing compressive sensing with a data-driven machine learning framework. We implement a generative adversarial network for image reconstruction without relying on a sample sparsity constraint. The proposed method outperforms the conventional compressive imaging algorithms in terms of image quality and noise robustness. We experimentally demonstrate speckle-based imaging below the diffraction limit at a sub-Nyquist speed through a multimode fiber.
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Double-slit photoelectron interference in strong-field ionization of the neon dimer
- Exploiting disorder for perfect focusing
- Learning to see through multimode fibers
- Optimizing the Latent Space of Generative Networks
- Learning and avoiding disorder in multimode fibers
- Deeply Sub-Wavelength Localization with Reverberation-Coded-Aperture
- Compressive three-dimensional super-resolution microscopy with speckle-saturated fluorescence excitation
- SPI-GAN: Towards Single-Pixel Imaging through Generative Adversarial Network