计算机科学
人工智能
迭代重建
计算机视觉
卷积神经网络
杠杆(统计)
深度学习
特征(语言学)
人工神经网络
模式识别(心理学)
语言学
哲学
作者
Xiuxi Pan,Xiaohong Chen,Saori Takeyama,Masahiro Yamaguchi
出处
期刊:Optics Letters
[Optica Publishing Group]
日期:2022-03-31
卷期号:47 (7): 1843-1843
被引量:21
摘要
A mask-based lensless camera optically encodes the scene with a thin mask and reconstructs the image afterward. The improvement of image reconstruction is one of the most important subjects in lensless imaging. Conventional model-based reconstruction approaches, which leverage knowledge of the physical system, are susceptible to imperfect system modeling. Reconstruction with a pure data-driven deep neural network (DNN) avoids this limitation, thereby having potential to provide a better reconstruction quality. However, existing pure DNN reconstruction approaches for lensless imaging do not provide a better result than model-based approaches. We reveal that the multiplexing property in lensless optics makes global features essential in understanding the optically encoded pattern. Additionally, all existing DNN reconstruction approaches apply fully convolutional networks (FCNs) which are not efficient in global feature reasoning. With this analysis, for the first time to the best of our knowledge, a fully connected neural network with a transformer for image reconstruction is proposed. The proposed architecture is better in global feature reasoning, and hence enhances the reconstruction. The superiority of the proposed architecture is verified by comparing with the model-based and FCN-based approaches in an optical experiment.
科研通智能强力驱动
Strongly Powered by AbleSci AI