An Image Morphing Technique Based on Optimal Mass Preserving Mapping
An Image Morphing Technique Based on Optimal Mass Preserving Mapping
复制标题
DOI：
10.1109/tip.2007.896637
复制
发表时间：
2007-06
影响因子：
10.6
通讯作者：
Lei Zhu;Yan Yang;S. Haker;A. Tannenbaum
中科院分区：
文献类型：
--
作者：
Lei Zhu;Yan Yang;S. Haker;A. Tannenbaum
图像变形，或图像插值在时间域中，处理一个图像到另一个的变形。基于最优质量输运理论，提出了一类新的图像变形算法。通过增加强度惩罚项来修改L2质量移动能量泛函，以便减少不期望的双重曝光效应。它是一种基于强度的方法，因此是无参数的。使用迭代梯度下降法计算最优扭曲函数。该变形方法还被扩展到双连通域，使用谐波参数化技术，沿着有限元方法
Image morphing, or image interpolation in the time domain, deals with the metamorphosis of one image into another. In this paper, a new class of image morphing algorithms is proposed based on the theory of optimal mass transport. The L2 mass moving energy functional is modified by adding an intensity penalizing term, in order to reduce the undesired double exposure effect. It is an intensity-based approach and, thus, is parameter free. The optimal warping function is computed using an iterative gradient descent approach. This proposed morphing method is also extended to doubly connected domains using a harmonic parameterization technique, along with finite-element methods