斑点图案
散斑噪声
散射
计算机科学
忠诚
正规化(语言学)
光学
深度学习
人工智能
人工神经网络
计算机视觉
物理
电信
作者
Fu Liu,Xiangjiao Meng,Yongkai Yin,Xiulun Yang
出处
期刊:Optics Letters
[The Optical Society]
日期:2023-10-04
卷期号:48 (20): 5285-5285
摘要
Imaging through a scattering medium is of great significance in many areas. Especially, speckle correlation imaging has been valued for its noninvasiveness. In this work, we report a deep learning solution that incorporates the physical model and an additional regularization for high-fidelity speckle correlation imaging. Without large-scale data to train, the physical model and regularization prior provide a correct direction for neural network to precisely reconstruct hidden objects from speckle under different scattering scenarios and noise levels. Experimental results demonstrate that the proposed method presents a significant advance in improving generalization and combating the invasion of noise.
科研通智能强力驱动
Strongly Powered by AbleSci AI