Generic interactive pixel-level image editing

Generic interactive pixel-level image editing
复制标题

通用交互式像素级图像编辑

DOI:
10.1111/cgf.13813
复制
发表时间:
2019
影响因子:
2.5
通讯作者:
Munoz A.
Munoz A.
中科院分区:
计算机科学4区
文献类型:
--
作者:
Liang Y.;Gan Y.;Chen M.;Gutierrez D.;Munoz A.

文献摘要

相似文献

在过去的几十年里,人们提出了几种图像编辑方法,取得了辉煌的成果。然而,其中最复杂的方法需要每像素额外的信息。例如,去雾需要每个像素特定的透光率值,或者景深模糊需要每个像素的深度或视差值。这个额外的每像素值是通过精心设计的启发式方法或通过对捕获硬件的额外控制获得的,这通常是为特定的编辑应用程序量身定制的。然而,相比之下,我们提出了一个通用的编辑范例,它可以成为几个不同应用程序的基础。这种模式可以生成所需的每像素值和以交互速率生成的编辑结果,并且可以迭代地改进最小的用户输入。我们以如此快的速度获得每像素值的关键见解是将它们聚类成超像素,但是,不是每个超像素的恒定值(这会产生精度问题),我们有一个数学表达式来表示每个超像素的像素值:在我们的情况下,每个超像素的二阶多项式。这导致了线性最小二乘系统,有效地实现了快速的特定每像素值。我们在三个应用中说明了这种方法:景深模糊(从深度值),去雾(从透射率值)和色调映射(从亮度和对比度局部值),我们的方法在所有三个应用中都证明了良好的互动性和准确性。我们的技术还与一个公共数据集进行了评估,并进行了比较。
Several image editing methods have been proposed in the past decades, achieving brilliant results. The most sophisticated of them, however, require additional information per‐pixel. For instance, dehazing requires a specific transmittance value per pixel, or depth of field blurring requires depth or disparity values per pixel. This additional per‐pixel value is obtained either through elaborated heuristics or through additional control over the capture hardware, which is very often tailored for the specific editing application. In contrast, however, we propose a generic editing paradigm that can become the base of several different applications. This paradigm generates both the needed per‐pixel values and the resulting edit at interactive rates, with minimal user input that can be iteratively refined. Our key insight for getting per‐pixel values at such speed is to cluster them into superpixels, but, instead of a constant value per superpixel (which yields accuracy problems), we have a mathematical expression for pixel values at each superpixel: in our case, an order two multinomial per superpixel. This leads to a linear least‐squares system, effectively enabling specific per‐pixel values at fast speeds. We illustrate this approach in three applications: depth of field blurring (from depth values), dehazing (from transmittance values) and tone mapping (from brightness and contrast local values), and our approach proves both favorably interactive and accurate in all three. Our technique is also evaluated with a common dataset and compared favorably.