A Data-Driven Approach to Efficient Character Articulation
A Data-Driven Approach to Efficient Character Articulation
复制标题
DOI：
10.1109/cadgraphics.2013.11
复制
发表时间：
2013-11
期刊：
影响因子：
--
通讯作者：
Yin Chen;Yu-Kun Lai;Zhi-Quan Cheng;Ralph Robert Martin;Shiyao Jin
中科院分区：
文献类型：
--
作者：
Yin Chen;Yu-Kun Lai;Zhi-Quan Cheng;Ralph Robert Martin;Shiyao Jin
在本文中，我们提出了一种数据驱动的方法，用于铰接网格的真实变形：姿势数据的广泛可用性使这种方法变得可行。我们使用多个参考模型，并结合局部空间中的快速线性混合蒙皮（LBS）方法。通过利用参考模型中的信息，实现了真实的变形，同时计算效率与传统混合方法相当——我们的方法适合实时应用。我们使用各种示例来证明我们算法的有效性。
In this paper, we propose a data-driven approach for realistic deformation of articulated meshes: the wide availability of pose data makes such an approach feasible. We use multiple reference models, combined with a fast linear blending skinning (LBS) method in local spaces. By exploiting information from the reference models, realistic deformation is achieved, yet with computational efficiency comparable to traditional blending methods-our approach is suitable for real-time applications. We demonstrate the effectiveness of our algorithm using various examples.