L_0梯度极小化耦合梯度保真的保结构图像平滑

图像平滑是计算机图形学和图像处理领域中最为重要的工具之一,其主要挑战在于平滑输入图像细节的同时如何保持原图像的显著结构特征.近几年,一种基于L0梯度极小化的图像平滑方法被提出,不仅视觉上效果出色,而且其局部均一的效果较之以往方法更为显著,然而,现有的基于L0的方法会产生阶梯效应且容易丢失部分结构.本文提出一种结合L0梯度极小化和梯度保真的平滑方法.该方法可以在保留图像主要结构的同时克服传统方法的阶梯效应,且保持包括颜色近似处在内的图像结构.实验结果表明了新方法可用于图像融合、边缘提取、JPEG格式卡通画压缩痕迹移除等应用.

Structure-preserving image smoothing with L0 gradient mini- mization coupling gradient fidelity term

hnage smoothing is a fundamental tool in computer graphics and image processing, whose major challenge is to smooth the input image while preserving its salient structure features. Recently, a piecewise smooth approach called L0 gradient minimization has been proposed for image smoothing. It employs gradient sparsity to achieve locally identical effect, which excels existing methods, making the visual performance more satisfying. However. methods based on Lo gradient minimization can easily cause staircase effect and lose part of structure. In this paper, we make the best of L0 gradient minimization and gradient fidelity term to present a new smoothing method. Our method can maintain the main structure of the image and restrain the staircase effect to make the gradient smoother. The essential structure in similar RGB values is preserved as well. Experimental results ilhtstrate that our method applies widely, and particularly beneficial to inmge composition, edge detection and clip-art JPEG artifact removal, etc.