Image Reconstruction for Quanta Image Sensors Using Deep Neural Networks
Image Reconstruction for Quanta Image Sensors Using Deep Neural Networks
复制标题
DOI：
10.1109/icassp.2018.8461685
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
J. H. Choi;Omar A. Elgendy;Stanley H. Chan
中科院分区：
文献类型：
--
作者：
J. H. Choi;Omar A. Elgendy;Stanley H. Chan
量子图像传感器（QIS）是一种单光子图像传感器，它对光场进行过采样以生成二进制测量。其单光子灵敏度使其成为继CMOS之后下一代图像传感器的理想候选者。然而，传感器的图像重建仍然是一个具有挑战性的问题。现有的图像重建算法主要是基于优化的。在本文中，我们提出了第一种用于QIS图像重建的深度神经网络方法。我们的深度神经网络以QIS的二进制比特流为输入，同时学习非线性变换和去噪。实验结果表明，该网络产生显着更好的重建结果相比，现有的方法。
Quanta Image Sensor (QIS) is a single-photon image sensor that oversamples the light field to generate binary measurements. Its single-photon sensitivity makes it an ideal candidate for the next generation image sensor after CMOS. However, image reconstruction of the sensor remains a challenging issue. Existing image reconstruction algorithms are largely based on optimization. In this paper, we present the first deep neural network approach for QIS image reconstruction. Our deep neural network takes the binary bit stream of QIS as input, learns the nonlinear transformation and denoising simultaneously. Experimental results show that the proposed network produces significantly better reconstruction results compared to existing methods.