On the use of differentiable optical models for lens and neural network co-design

M. Dufraisse; P. Trouvé-Peloux; J.-B. Volatier; F. Champagnat

doi:10.1117/12.2621464

20 May 2022 On the use of differentiable optical models for lens and neural network co-design

M. Dufraisse, P. Trouvé-Peloux, J.-B. Volatier, F. Champagnat

Proceedings Volume 12136, Unconventional Optical Imaging III; 121360N (2022) https://doi.org/10.1117/12.2621464
Event: SPIE Photonics Europe, 2022, Strasbourg, France

Abstract

Co-design methods started to incorporate neural networks a few years ago when deep learning showed promising results in computer vision. This requires the computation of the point spread function (PSF) of an optical system as well as its gradients with respect to the optical parameters so that they can be optimized using gradient descent. In previous works, several approaches have been proposed to obtain the PSF, most notably using paraxial optics, Fourier optics or differential ray tracers. All these models have limitations and strengths regarding their ability to compute a precise PSF and their computational cost. We propose to compare them in a simple co-design task to discuss their relevance. We will discuss the computational cost of these methods as well as their applicability.

Conference Presentation

Citation Download Citation

M. Dufraisse, P. Trouvé-Peloux, J.-B. Volatier, and F. Champagnat "On the use of differentiable optical models for lens and neural network co-design", Proc. SPIE 12136, Unconventional Optical Imaging III, 121360N (20 May 2022); https://doi.org/10.1117/12.2621464

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available