Small-brain neural networks rapidly solve inverse problems with vortex Fourier encoders
arXiv:2005.07682 · doi:10.1364/OPTICA.397707
Abstract
We introduce a vortex phase transform with a lenslet-array to accompany shallow, dense, ``small-brain'' neural networks for high-speed and low-light imaging. Our single-shot ptychographic approach exploits the coherent diffraction, compact representation, and edge enhancement of Fourier-tranformed spiral-phase gradients. With vortex spatial encoding, a small brain is trained to deconvolve images at rates 5-20 times faster than those achieved with random encoding schemes, where greater advantages are gained in the presence of noise. Once trained, the small brain reconstructs an object from intensity-only data, solving an inverse mapping without performing iterations on each image and without deep-learning schemes. With this hybrid, optical-digital, vortex Fourier encoded, small-brain scheme, we reconstruct MNIST Fashion objects illuminated with low-light flux (5 nJ/cm) at a rate of several thousand frames per second on a 15 W central processing unit, two orders of magnitude faster than convolutional neural networks.
References in corpus (15)
- All-Optical Machine Learning Using Diffractive Deep Neural Networks
- Deep speckle correlation: a deep learning approach towards scalable imaging through scattering media
- Metasurface interferometry towards quantum sensors
- Extended depth-of-field in holographic image reconstruction using deep learning based auto-focusing and phase-recovery
- Probing 10 μK stability and residual drifts in the cross-polarized dual-mode stabilization of single-crystal ultrahigh-Q optical resonators
- A Photonic Crystal Slab Laplace Differentiator
- High-index dielectric metasurfaces performing mathematical operations
- Noninvasive nonlinear imaging through strongly-scattering turbid layers
- Spectral Representations for Convolutional Neural Networks
- Physical meaning of the radial index of Laguerre-Gauss beams
- Geometric Metasurface Fork Gratings for Vortex Beam Generation and Manipulation
- Deep learning-based super-resolution in coherent imaging systems
- Light scattering control in transmission and reflection with neural networks
- Real-time coherent diffraction inversion using deep generative networks
- Iterative phase retrieval in coherent diffractive imaging: practical issues
Cited by in corpus (6)
- Nonlinear optical encoding enabled by recurrent linear scattering
- Ultrafast Microscopy of a Plasmonic Spin Skyrmion
- Robust Position Sensing with Wave Fingerprints in Dynamic Complex Environments
- Polarimetric compressed sensing with hollow, self-assembled diffractive films
- Learning Illumination Patterns for Coded Diffraction Phase Retrieval
- Compute-first optical detection for noise-resilient visual perception