多模光纤
计算机科学
人工神经网络
人工智能
图像分辨率
反问题
纤维
光学
光纤
物理
材料科学
电信
数学
数学分析
复合材料
作者
Wei Li,Ksenia A. Abrashitova,Lyubov V. Amitonova
出处
期刊:Optics Letters
[Optica Publishing Group]
日期:2023-05-23
卷期号:48 (13): 3363-3363
被引量:25
摘要
Multimode fiber endoscopes provide extreme miniaturization of imaging components for minimally invasive deep tissue imaging. Typically, such fiber systems suffer from low spatial resolution and long measurement time. Fast super-resolution imaging through a multimode fiber has been achieved by using computational optimization algorithms with hand-picked priors. However, machine learning reconstruction approaches offer the promise of better priors, but require large training datasets and therefore long and unpractical pre-calibration time. Here we report a method of multimode fiber imaging based on unsupervised learning with untrained neural networks. The proposed approach solves the ill-posed inverse problem by not relying on any pre-training process. We have demonstrated both theoretically and experimentally that untrained neural networks enhance the imaging quality and provide sub-diffraction spatial resolution of the multimode fiber imaging system.
科研通智能强力驱动
Strongly Powered by AbleSci AI