Improvement of Colorization Realism via the Structure Tensor
Improvement of Colorization Realism via the Structure Tensor
复制标题
DOI：
10.1142/s0219467811004214
复制
发表时间：
2011-10
期刊：
影响因子：
--
通讯作者：
M. S. Drew;G. Finlayson
中科院分区：
文献类型：
--
作者：
M. S. Drew;G. Finlayson
着色是一种颜色操作机制，使用用户辅助的颜色提示将灰度图像更改为彩色图像。已经构造了几种着色算法，其中许多方法能够在给定用户提供的令人惊讶的稀疏提示集的情况下生成适当着色的图像。然而，这些彩色图像实际上可能看起来并不真实。此外，彩色图像中的对比度可能与原始灰度图像中感知到的梯度不匹配。我们认为，正是这种偏离了原来的梯度，导致了一些着色的不真实外观。为了纠正这一点，我们利用由结构张量导出的彩色图像的Di Zenzo梯度，并调整彩色图像，使最大对比度梯度的Di Zenzo定义与原始灰度图像中的梯度一致。为此，我们提出了一种启发式方法，并在此方法的指导下设计了一种基于优化的方法。我们的梯度投影倾向于在调整后的颜色中产生更自然的图像。为了探索所提出的方法，我们利用极简的颜色提示集，并特别发现不现实颜色的“热点”被柔和到更现实的颜色区域。本文的目的不是介绍一种新的基本着色，而是我们的方法是为了使任何着色看起来更逼真；我们将演示几种不同的基本方法的情况。事实上，我们甚至发现可以使用一种非常简单的着色算法，只要这里提出的投影可以使着色看起来更逼真。
Colorization is a color manipulation mechanism employing user-assisted color hints for changing grayscale images into colored ones. Several colorization algorithms have been constructed, and many of these methods are able to produce appropriately colorized images given a surprisingly sparse set of hints supplied by the user. However, these color images may not in fact look realistic. Moreover, the contrast in the colorized image may not match the gradient perceived in the original grayscale image. We argue that it is this departure from the original gradient that contributes to the unreal appearance in some colorizations. To correct this, we make use of the Di Zenzo gradient of a color image derived from the structure tensor, and adjust the colorized image such that the Di Zenzo definition of the maximum-contrast gradient agrees with the gradient in the original gray image. We present a heuristic method to this end and guided by this approach devise an optimization-based method. Our gradient projection tends to result in more natural-looking images in the resulting adjusted colorization. To explore the proposed method we utilize minimalist sets of color hints and find in particular that "hotspots" of unrealistic color are subdued into regions of more realistic color. This paper is not aimed at introducing a new basic colorization but instead our method is meant to make any colorization look more realistic; we demonstrate that this is the case for several different basic methods. In fact, we even find that a very simplistic colorization algorithm can be used provided the projection proposed here is then used to make the colorization more realistic looking.