基于形状插值与移动最小二乘变形的图像渐变

Image Morphing Using Shape Interpolation and MLS Deformation

针对已有图像渐变方法难以处理较大几何变化的问题,提出一种基于形状插值与移动最小二乘变形的图像渐变方法.给定一幅源图像和一幅目标图像,用户首先通过在图像上放置开或者封闭的曲线(称为"特征曲线"),对齐源和目标图像中的几何特征;然后提出一种基于重心的线条外观模型,以提取表示一组特征曲线的形状及其所传达的视觉外观,并建立一种双层结构的形状插值算法,实现源特征曲线到目标特征曲线的保形状过渡;最后以中间过渡特征曲线为约束,通过保刚性的移动最小二乘变形把2幅图像的几何特征融合在一起,生成保外观的中间过渡图像帧.实验结果表明,该方法能够实时生成自然且视觉真实的图像渐变序列,即使当源和目标图像中对应几何特征的形状差别较大时,也能够充分保持这些特征的外观和属性.

This paper presents an image morphing technique which is based on shape interpolation and movingleast squares deformation.In the algorithm,the features of the source and target images are at first manuallyspecified using open or closed curves(called as“feature curves”)and then the source image is automaticallytransformed into the target image in a natural way.In order to retain the original appearance and properties inthe in-between objects,a barycenter-based shape model is designed to represent the visual appearance of a setof curves.Upon this model,a two-level shape interpolation is introduced to generate a sequence of intermediatefeature curves which is appearance-preserving.During morphing,the intermediate feature curves are usedto align the geometric features of the source and target images via MLS deformation.Consequently,the originalappearance and properties of the objects can be effectively preserved in the intermediate images.We haveapplied our approach to a variety of examples to demonstrate its versatility and visual accuracy.