Complex Object Correspondence Construction in Two-Dimensional Animation
Complex Object Correspondence Construction in Two-Dimensional Animation
复制标题
DOI：
10.1109/tip.2011.2158225
复制
发表时间：
2011-11
影响因子：
10.6
通讯作者：
Jun Yu;Dongquan Liu;D. Tao;S. H. Soon
中科院分区：
文献类型：
--
作者：
Jun Yu;Dongquan Liu;D. Tao;S. H. Soon
关键帧中对象的对应构造是实现2-D计算机辅助动画制作中插补和着色的前提。由于动画的每个帧都由多个层组成，因此对象在形状和结构方面都很复杂。因此，现有的形状匹配算法专门设计用于简单的结构，如一个单一的封闭轮廓不能执行由多个轮廓与开放的形状构造的对象。本文介绍了一种半监督的补丁对齐框架，复杂对象的对应关系的建设。特别是，新的框架构造局部补丁的对象上的每个点，并在一个新的特征空间，其中对象之间的对应关系可以检测到的后续聚类这些补丁对齐。对于局部曲面片构造，用户通过引入两两约束条件来表示对应点（必须连接）或不匹配点（不能连接），从而提高了对应构造的性能。这种输入通过用户友好的界面方便动画软件用户。十几个实验结果对我们的卡通数据集，是建立在工业生产表明所提出的框架，用于构建复杂对象的对应关系的有效性。作为我们的框架的扩展，MPEG-7数据集上的额外形状检索实验表明，其性能与T-PAMI 2009年发表的一个突出的算法相媲美。
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.