[{"id":1167,"title":"Imaging through perturbed multimode fibers with physical prior","sha":"41a4aea7a03e4f27b1fa930a3aa0c7e4","user_id":null,"state":"published","body":"Imaging through perturbed multimode fibers based on deep learning has been widely researched. However, existing methods mainly use target-speckle pairs in different configurations. It is challenging to reconstruct targets without trained networks. In this paper, we propose a physics-assisted, unsupervised, learning-based fiber imaging scheme. The role of the physical prior is to simplify the mapping relationship between the speckle pattern and the target image, thereby reducing the computational complexity. The learning model learns target features according to the optimized direction provided by the physical model. Then, the reconstruction process of the learning model only requires a few speckle patterns and unpaired targets. The proposed scheme also increases the generalization ability of the learning-based method in perturbed multimode fibers and targets. Our scheme has the potential to extend the application of MMF imaging. ","created_at":"2023-10-26T02:52:48.267Z","updated_at":"2023-11-16T06:00:26.697Z","zenodo_id":10140327,"doi":"https://doi.org/10.5281/zenodo.10140327","subject":null,"tags":["multimode fiber","unsupervised network","physical prior"],"vote_count":0,"view_count":1,"score":0.1,"deleted":false,"muted":false,"tweeted":false,"attachment_file_name":null,"attachment_content_type":null,"attachment_file_size":null,"attachment_updated_at":null}]