AI and Optical Data Sciences V最新文献

筛选

英文中文

Massively parallel all-optical visual computing using a wavelength-multiplexed diffractive optical processor 利用波长多路复用衍射光学处理器进行大规模并行全光学视觉计算

AI and Optical Data Sciences V Pub Date : 2024-03-13 DOI: 10.1117/12.3001971

Jingxi Li, Tianyi Gan, Bijie Bai, Yilin Luo, Mona Jarrahi, Aydogan Ozcan

引用次数: 0

Reflection-mode transmission matrix reconstruction using neural networks in optical fiber imaging systems 在光纤成像系统中利用神经网络重建反射模式传输矩阵

AI and Optical Data Sciences V Pub Date : 2024-03-13 DOI: 10.1117/12.3001414

Yijie Zheng, G. Gordon

引用次数: 0

Enhancing digital hologram reconstruction using reverse-attention loss for untrained physics-driven deep learning models with uncertain distance 利用反向注意力损失增强数字全息图重建，适用于距离不确定的未训练物理驱动深度学习模型

AI and Optical Data Sciences V Pub Date : 2024-01-11 DOI: 10.1117/12.3005570

Xiwen Chen, Hao Wang, Zhao Zhang, Zhenmin Li, Huayu Li, Tong Ye, A. Razi

{"title":"Enhancing digital hologram reconstruction using reverse-attention loss for untrained physics-driven deep learning models with uncertain distance","authors":"Xiwen Chen, Hao Wang, Zhao Zhang, Zhenmin Li, Huayu Li, Tong Ye, A. Razi","doi":"10.1117/12.3005570","DOIUrl":"https://doi.org/10.1117/12.3005570","url":null,"abstract":"Untrained Physics-based Deep Learning (DL) methods for digital holography have gained significant attention due to their benefits, such as not requiring an annotated training dataset, and providing interpretability since utilizing the governing laws of hologram formation. However, they are sensitive to the hard-to-obtain precise object distance from the imaging plane, posing the $textit{Autofocusing}$ challenge. Conventional solutions involve reconstructing image stacks for different potential distances and applying focus metrics to select the best results, which apparently is computationally inefficient. In contrast, recently developed DL-based methods treat it as a supervised task, which again needs annotated data and lacks generalizability. To address this issue, we propose $textit{reverse-attention loss}$, a weighted sum of losses for all possible candidates with learnable weights. This is a pioneering approach to addressing the Autofocusing challenge in untrained deep-learning methods. Both theoretical analysis and experiments demonstrate its superiority in efficiency and accuracy. Interestingly, our method presents a significant reconstruction performance over rival methods (i.e. alternating descent-like optimization, non-weighted loss integration, and random distance assignment) and even is almost equal to that achieved with a precisely known object distance. For example, the difference is less than 1dB in PSNR and 0.002 in SSIM for the target sample in our experiment.","PeriodicalId":517856,"journal":{"name":"AI and Optical Data Sciences V","volume":"50 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140509948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页