Full characterization of partially measured systems with neural networks

Babak Rahmani,Damien Loterie,Eirini Kakkava,Navid Borhani,Ugur Tegin,Demetri Psaltis,Christophe Moser

2021 CONFERENCE ON LASERS AND ELECTRO-OPTICS EUROPE & EUROPEAN QUANTUM ELECTRONICS CONFERENCE (CLEO/EUROPE-EQEC)（2021）

引用 0|浏览2

暂无评分

摘要

We propose a method based on neural networks to characterize a complex optical system from intensity-only measurements. The characterization involves learning the forward and backward mappings of the system that can be subsequently used to project or image arbitrary patterns. © 2021 The Author(s)

查看译文

关键词

neural networks,complex optical system,intensity-only measurements,forward mappings,backward mappings,partially measured systems,discriminator network training,generator network training,target images,image capture,camera

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要