Department of Computer Science, Xiamen University, Xiamen, China.
IEEE Trans Image Process. 2011 Nov;20(11):3257-69. doi: 10.1109/TIP.2011.2158225. Epub 2011 May 31.
Correspondence construction of objects in key frames is the precondition for inbetweening and coloring in 2-D computer-assisted animation production. Since each frame of an animation consists of multiple layers, objects are complex in terms of shape and structure. Therefore, existing shape-matching algorithms specifically designed for simple structures such as a single closed contour cannot perform well on objects constructed by multiple contours with an open shape. This paper introduces a semisupervised patch alignment framework for complex object correspondence construction. In particular, the new framework constructs local patches for each point on an object and aligns these patches in a new feature space, in which correspondences between objects can be detected by the subsequent clustering. For local patch construction, pairwise constraints, which indicate the corresponding points (must link) or unfitting points (cannot link), are introduced by users to improve the performance of correspondence construction. This kind of input is convenient for animation software users via user-friendly interfaces. A dozen of experimental results on our cartoon data set that is built on industrial production suggest the effectiveness of the proposed framework for constructing correspondences of complex objects. As an extension of our framework, additional shape retrieval experiments on MPEG-7 data set show that its performance is comparable with that of a prominent algorithm published in T-PAMI 2009.
关键帧中目标的对应构造是二维计算机辅助动画制作中插补和上色的前提。由于动画的每一帧都由多个图层组成，因此对象在形状和结构上都很复杂。因此，现有的专门针对简单结构（如单个封闭轮廓）设计的形状匹配算法在处理由多个具有开放形状的轮廓构建的对象时效果不佳。本文介绍了一种用于复杂对象对应构造的半监督补丁对齐框架。具体来说，新框架为对象上的每个点构造局部补丁，并在新的特征空间中对齐这些补丁，其中对象之间的对应关系可以通过后续的聚类来检测。对于局部补丁构造，通过用户引入的成对约束（指示对应点（必须链接）或不匹配点（不能链接））来提高对应构造的性能。这种输入方式通过用户友好的界面方便了动画软件用户。我们在工业生产中构建的卡通数据集上进行了十几个实验，结果表明，该框架对于构建复杂对象的对应关系是有效的。作为我们框架的扩展，在 MPEG-7 数据集上进行的附加形状检索实验表明，其性能可与 2009 年在 T-PAMI 上发表的一种突出算法相媲美。
