当前位置: X-MOL 学术IEEE Trans. Vis. Comput. Graph. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Colorization Framework for Monochrome-Color Dual-Lens Systems Using a Deep Convolutional Network
IEEE Transactions on Visualization and Computer Graphics ( IF 5.2 ) Pub Date : 2020-09-08 , DOI: 10.1109/tvcg.2020.3022480
Xuan Dong 1 , Weixin Li 2 , Xiaoyan Hu 1 , Xiaojie Wang 1 , Yunhong Wang 2
Affiliation  

In monochrome-color dual-lens systems, the monochrome camera can capture images with higher quality than the color camera. To obtain high quality color images, a better approach is to colorize the gray images from the monochrome camera with the color images from the color camera serving as a reference. In addition, the colorization may fail in some cases, which makes the estimation of the colorization quality a necessary step before outputting the colorization result. To solve these problems, we propose a deep convolutional network based framework. 1) In the colorization module, the proposed colorization CNN uses deep feature representations, attention operation, 3-D regulation and color correction to make use of colors of multiple pixels in the reference image for colorizing each pixel in the input gray image. 2) In the colorization quality estimation module, based on the symmetry property of colorization, we propose to utilize the colorization CNN again to colorize the gray map of the original reference color image using the first-time colorization result from the colorization module as reference. Then, the quality loss of the second-time colorization result can be used for estimating the colorization quality. Experimental results show that our method can largely outperform the state-of-the-art colorization methods and estimate the colorization quality accurately as well.

中文翻译:

使用深度卷积网络的单色双镜头系统的着色框架

在单色双镜头系统中,单色相机可以捕捉到比彩色相机更高质量的图像。为了获得高质量的彩色图像,更好的方法是对来自单色相机的灰度图像进行着色,并以彩色相机的彩色图像作为参考。此外,在某些情况下着色可能会失败,这使得在输出着色结果之前对着色质量的估计成为必要的步骤。为了解决这些问题,我们提出了一个基于深度卷积网络的框架。1)在着色模块中,提出的着色CNN使用深度特征表示、注意力操作、3-D调节和颜色校正,利用参考图像中多个像素的颜色对输入灰度图像中的每个像素进行着色。2)在着色质量估计模块中,基于着色的对称性,我们提出以着色模块的首次着色结果为参考,再次利用着色CNN对原始参考彩色图像的灰度图进行着色。然后,可以使用第二次着色结果的质量损失来估计着色质量。实验结果表明,我们的方法可以在很大程度上优于最先进的着色方法,并且还可以准确地估计着色质量。第二次着色结果的质量损失可用于估计着色质量。实验结果表明,我们的方法可以在很大程度上优于最先进的着色方法,并且还可以准确地估计着色质量。第二次着色结果的质量损失可用于估计着色质量。实验结果表明,我们的方法可以在很大程度上优于最先进的着色方法,并且还可以准确地估计着色质量。
更新日期:2020-09-08
down
wechat
bug