Model Transduction for Triangle Meshes

• Published in: Journal of computer science and technology Vol. 25; no. 3; pp. 583 - 594
• Main Author: 吴怀宇 潘春洪 查红彬 马颂德
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01.05.2010; Springer Nature B.V; National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China%National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China%Key Laboratory of Machine Perception(MOE),Peking University,Beijing 100871,China; Key Laboratory of Machine Perception(MOE),Peking University,Beijing 100871,China
• Subjects: Animation; Approximation; Artificial Intelligence; Computer Science; Correspondence; Data Structures and Information Theory; Deformation; Deformation effects; Editing; Finite element method; Information Systems Applications (incl.Internet); Laboratories; Linear systems; Manifolds; Mathematical models; Methods; Motion capture; Operators; Phases; Reference materials; Regular Paper; Science; Software Engineering; Theory of Computation; Three dimensional motion; Translations; Triangles; 三角网格模型; 传递方法; 变形动画; 对应关系; 应用程序; 编辑操作; 运动捕捉; mesh deformation; cross-parameterization; mean-value manifold operator; retargetting; model transduction
• ISSN: 1000-9000; 1860-4749
• DOI: 10.1007/s11390-010-9347-8

This paper proposes a novel method, called model transduction, to directly transfer pose between different meshes, without the need of building the skeleton configurations for meshes. Different from previous retargetting methods, such as deformation transfer, model transduction does not require a reference source mesh to obtain the source deformation, thus effectively avoids unsatisfying results when the source and target have different reference poses. Moreover, we show other two applications of the model transduction method： pose correction after various mesh editing operations, and skeleton-free deformation animation based on 3D Mocap （Motion capture） data. Model transduction is based on two ingredients： model deformation and model correspondence. Specifically, based on the mean-value manifold operator, our mesh deformation method produces visually pleasing deformation results under large angle rotations or big-scale translations of handles. Then we propose a novel scheme for shape-preserving correspondence between manifold meshes. Our method fits nicely in a unified framework, where the similar type of operator is applied in all phases. The resulting quadratic formulation can be efficiently minimized by fast solving the sparse linear system. Experimental results show that model transduction can successfully transfer both complex skeletal structures and subtle skin deformations.