Research and Application of Example-Driven Surface Deformation Method

• Published in: Chinese Journal of Electronics Vol. 28; no. 1; pp. 85 - 92
• Main Authors: Qin, Xuzhou, Wu, Tieru, Liu, Yipeng, Lu, Yinan
• Format: Journal Article
• Language: English
• Published: Published by the IET on behalf of the CIE 01.01.2019
• Subjects: challenging work; computational geometry; computer animation; Deformation; deformations; Example‐driven; example‐driven approach; example‐driven deformation methods; example‐driven surface deformation method; experimental results; geometrically complex mesh; image reconstruction; interactive mesh deformation; interpolation; mesh generation; Mesh representation; modeling process; multiple shapes; natural deformation results; producing realistic deformation result; Reconstruction; reconstruction framework; reconstruction method; rotation invariant feature representation; semantic deformation transfer; shape space; solid modelling; computational geometry; Example-driven; reconstruction framework; interactive mesh deformation; Mesh representation; semantic deformation transfer; computer animation; natural deformation results; producing realistic deformation result; deformations; deformation; multiple shapes; Reconstruction; example-driven surface deformation method; experimental results; reconstruction method; mesh generation; image reconstruction; rotation invariant feature representation; geometrically complex mesh; interpolation; modeling process; example-driven approach; example-driven deformation methods; challenging work; shape space; solid modelling
• ISSN: 1022-4653; 2075-5597
• DOI: 10.1049/cje.2018.10.005

Despite the large work made in interactive mesh deformation, manipulating a geometrically complex mesh and producing realistic deformation result is still a challenging work. Example-driven deformation methods distinctly simplify the modeling process and produce realistic deformation result by incorporating knowledge learned from shape space. We introduce a rotation invariant feature representation and a reconstruction framework to accurately reconstruct the vertex positions. Our feature representation allows both interpolation as well as extrapolation and can effectively blend multiple shapes. Based on this, we achieve an example-driven approach to mesh deformations. By using a collection of models as examples, our method produces natural deformation results guided by them even with large movement of handles. We will apply our representation and reconstruction method to semantic deformation transfer. The experimental results have demonstrated the effectiveness of the proposed methods.