Light Field Neural Network

09/19/2018
by   Yuchi Huo, et al.
0

We introduce an optical neural network system made by off-the-shelf components. Compared to electronic systems, the proposed system can execute advanced inference tasks on the speed of light and much lower power consumption. By using see-through screens and optical components, it can support a programmable optical neural network, see-through display, and incoherent light processor. Various application prototypes are discussed as extensions of basic layers including optical computation, light field display, augmented reality, and passive light/image processing.

READ FULL TEXT
research
04/12/2021

A multi-plane augmented reality head-up display system based on volume holographic optical elements with large area

The traditional head-up display (HUD) system has the disadvantages of a ...
research
09/17/2023

All-optical image denoising using a diffractive visual processor

Image denoising, one of the essential inverse problems, targets to remov...
research
11/04/2022

DAD vision: opto-electronic co-designed computer vision with division adjoint method

The miniaturization and mobility of computer vision systems are limited ...
research
12/23/2019

An optical diffractive deep neural network with multiple frequency-channels

Diffractive deep neural network (DNNet) is a novel machine learning fram...
research
11/30/2021

Sparse deep computer-generated holography for optical microscopy

Computer-generated holography (CGH) has broad applications such as direc...
research
08/16/2017

Light in Power: A General and Parameter-free Algorithm for Caustic Design

We present in this paper a generic and parameter-free algorithm to effic...
research
11/01/2021

Geometrical holographic display

Is it possible to realize a holographic display with commercial availabl...

Please sign up or login with your details

Forgot password? Click here to reset