Convolutional demosaicing network for joint chromatic and polarimetric imagery
Convolutional demosaicing network for joint chromatic and polarimetric imagery
复制标题
用于联合彩色和偏振图像的卷积去马赛克网络
DOI：
10.1364/ol.44.005646
复制
发表时间：
2019-11-15
期刊：
影响因子：
3.6
通讯作者：
Zhao, Qinping
中科院分区：
文献类型：
--
作者：
Wen, Sijia;Zheng, Yinqiang;Zhao, Qinping
由于图像传感器制造技术的最新进展，配备RGGB拜耳滤光片和定向偏振滤光片的传感器的出现为需要RGB和偏振信息的计算机视觉任务带来了显著优势。在这方面，联合彩色和偏振图像去马赛克是必不可少的。然而，作为一种新型的阵列方向图，目前还没有专门的方法来完成这一具有挑战性的任务。在这封信中，我们收集了第一个彩色偏振数据集，并提出了一个彩色偏振去马赛克网络（CPDNet）来解决这个联合彩色和偏振图像去马赛克问题。提出的CPDNet由残差块和具有定制损失函数的多任务结构组成。实验结果表明，我们提出的方法是能够忠实地恢复完整的12通道的彩色和偏振信息，每个像素从一个单一的马赛克图像的定量措施和视觉质量。(C)2019美国光学学会
Due to the latest progress in image sensor manufacturing technology, the emergence of a sensor equipped with an RGGB Bayer filter and a directional polarizing filter has brought significant advantages to computer vision tasks where RGB and polarization information is required. In this regard, joint chromatic and polarimetric image demosaicing is indispensable. However, as a new type of array pattern, there is no dedicated method for this challenging task. In this Letter, we collect, to the best of our knowledge, the first chromatic-polarization dataset and propose a chromatic-polarization demosaicing network (CPDNet) to address this joint chromatic and polarimetric image demosaicing issue. The proposed CPDNet is composed of the residual block and the multi-task structure with the costumed loss function. The experimental results show that our proposed methods are capable of faithfully recovering full 12-channel chromatic and polarimetric information for each pixel from a single mosaic image in terms of quantitative measures and visual quality. (C) 2019 Optical Society of America