Twin Deep Convolutional Neural Network for Example-Based Image Colorization
Twin Deep Convolutional Neural Network for Example-Based Image Colorization
复制标题
DOI：
10.1007/978-3-319-64689-3_15
复制
发表时间：
2017-08
期刊：
影响因子：
--
通讯作者：
D. Varga;T. Szirányi
中科院分区：
文献类型：
--
作者：
D. Varga;T. Szirányi
本文研究了灰度图像的彩色化问题。最近的论文显示了利用各种深层体系结构进行图像彩色化的显著效果。与以前的方法不同，我们使用深度架构和参考图像进行彩色化。我们的体系结构采用两个具有相同结构的并行卷积神经网络。一个CNN使用参考图像，帮助另一个CNN对输入图像进行颜色预测。另一方面，使用输入图像的第二个CNN帮助识别保存关于场景配色方案的基本信息的区域。对SUN数据库图像和其他图像进行了全面的实验和定性和定量的评价。定量评价基于峰值信噪比(PSNR)和四元数结构相似性(QSSIM)。
This paper deals with the colorization of grayscale images. Recent papers have shown remarkable results on image colorization utilizing various deep architectures. Unlike previous methods, we perform colorization using a deep architecture and a reference image. Our architecture utilizes two parallel Convolutional Neural Networks which have the same structure. One CNN, which uses the reference image, helps the other CNN in color prediction for the input image. On the other hand, the second CNN, which uses the input image, helps to identify the areas which holds essential information about the color scheme of the scene. Comprehensive experiments and qualitative and quantitative evaluations were conducted on the images of SUN database and on other images. Quantitative evaluations are based on Peak Signal-to-Noise Ratio (PSNR) and on Quaternion Structural Similarity (QSSIM).