Small-brain neural networks rapidly solve inverse problems with vortex Fourier encoders

05/15/2020
by   Baurzhan Muminov, et al.
32

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^2) 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.

READ FULL TEXT

page 2

page 5

page 6

page 7

page 8

page 9

research
04/21/2021

Programmable 3D snapshot microscopy with Fourier convolutional networks

3D snapshot microscopy enables volumetric imaging as fast as a camera al...
research
08/06/2023

FourLLIE: Boosting Low-Light Image Enhancement by Fourier Frequency Information

Recently, Fourier frequency information has attracted much attention in ...
research
09/18/2022

MetaDIP: Accelerating Deep Image Prior with Meta Learning

Deep image prior (DIP) is a recently proposed technique for solving imag...
research
03/16/2020

u-net CNN based fourier ptychography

Fourier ptychography is a recently explored imaging method for overcomin...
research
05/15/2020

Machine Vision using Diffractive Spectral Encoding

Machine vision systems mostly rely on lens-based optical imaging archite...
research
05/31/2017

Micro Fourier Transform Profilometry (μFTP): 3D shape measurement at 10,000 frames per second

Recent advances in imaging sensors and digital light projection technolo...

Please sign up or login with your details

Forgot password? Click here to reset