Curriculum Learning for ab initio Deep Learned Refractive Optics

TL;DR

This paper introduces a curriculum learning-based method for designing complex optical lenses from scratch using deep learning, enabling fully automatic creation of advanced imaging systems without initial design constraints.

Contribution

It presents the first ab initio deep learning approach for compound lens design using curriculum learning, removing the need for human-designed initial structures.

Findings

Successfully designed classical imaging lenses automatically.

Created a large field-of-view extended depth-of-field lens.

Achieved highly aspheric surfaces in compact form factors.

Abstract

Deep optical optimization has recently emerged as a new paradigm for designing computational imaging systems using only the output image as the objective. However, it has been limited to either simple optical systems consisting of a single element such as a diffractive optical element (DOE) or metalens, or the fine-tuning of compound lenses from good initial designs. Here we present a DeepLens design method based on curriculum learning, which is able to learn optical designs of compound lenses ab initio from randomly initialized surfaces without human intervention, therefore overcoming the need for a good initial design. We demonstrate the effectiveness of our approach by fully automatically designing both classical imaging lenses and a large field-of-view extended depth-of-field computational lens in a cellphone-style form factor, with highly aspheric surfaces and a short back focal length.