Exploring Quasi-Global Solutions to Compound Lens Based Computational Imaging Systems

TL;DR

This paper introduces QGSO, a novel automated method for designing compound lens computational imaging systems that enhances global search capabilities and improves imaging quality through integrated optimization techniques.

Contribution

The work presents a new end-to-end lens design framework combining diverse initial search and physics-aware joint optimization, advancing automated compound lens design.

Findings

QGSO outperforms existing methods in global search ability.

Designed systems achieve higher imaging quality.

Framework is validated through extensive experiments.

Abstract

Recently, joint design approaches that simultaneously optimize optical systems and downstream algorithms through data-driven learning have demonstrated superior performance over traditional separate design approaches. However, current joint design approaches heavily rely on the manual identification of initial lenses, posing challenges and limitations, particularly for compound lens systems with multiple potential starting points. In this work, we present Quasi-Global Search Optics (QGSO) to automatically design compound lens based computational imaging systems through two parts: (i) Fused Optimization Method for Automatic Optical Design (OptiFusion), which searches for diverse initial optical systems under certain design specifications; and (ii) Efficient Physic-aware Joint Optimization (EPJO), which conducts parallel joint optimization of initial optical systems and image reconstruction networks with the consideration of physical constraints, culminating in the selection of the optimal solution in all search results. Extensive experimental results illustrate that QGSO serves as a transformative end-to-end lens design paradigm for superior global search ability, which automatically provides compound lens based computational imaging systems with higher imaging quality compared to existing paradigms. The source code will be made publicly available at https://github.com/LiGpy/QGSO.