Issue No. 08 - Aug. (2012 vol. 18)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TVCG.2012.88
Yue Qi , State Key Lab. of Virtual Reality Technol. & Syst., Beihang Univ., Beijing, China
Ling Zhao , State Key Lab. of Virtual Reality Technol. & Syst., Beihang Univ., Beijing, China
KangKang Yin , Dept. of Comput. Sci., Nat. Univ. of Singapore, Singapore, Singapore
Haoda Huang , Microsoft Res. Asia, Mountain View, CA, USA
Yizhou Yu , Univ. of Hong Kong, Hong Kong, China
Xin Tong , Microsoft Res. Asia, Beijing, China
Recent advances in laser scanning technology have made it possible to faithfully scan a real object with tiny geometric details, such as pores and wrinkles. However, a faithful digital model should not only capture static details of the real counterpart but also be able to reproduce the deformed versions of such details. In this paper, we develop a data-driven model that has two components; the first accommodates smooth large-scale deformations and the second captures high-resolution details. Large-scale deformations are based on a nonlinear mapping between sparse control points and bone transformations. A global mapping, however, would fail to synthesize realistic geometries from sparse examples, for highly deformable models with a large range of motion. The key is to train a collection of mappings defined over regions locally in both the geometry and the pose space. Deformable fine-scale details are generated from a second nonlinear mapping between the control points and per-vertex displacements. We apply our modeling scheme to scanned human hand models, scanned face models, face models reconstructed from multiview video sequences, and manually constructed dinosaur models. Experiments show that our deformation models, learned from extremely sparse training data, are effective and robust in synthesizing highly deformable models with rich fine features, for keyframe animation as well as performance-driven animation. We also compare our results with those obtained by alternative techniques.
video signal processing, computational geometry, computer animation, feature extraction, image reconstruction, image sequences, solid modelling, performance-driven animation, detail-preserving controllable deformation sparse examples, laser scanning technology, tiny geometric details, object pores, object wrinkles, faithful digital model, static detail capture, data-driven model, smooth large-scale deformation, high-resolution detail capture, nonlinear mapping, sparse control points, bone transformation, global mapping, geometry, pose space, per-vertex displacement, scanned human hand model, scanned face model, face model reconstruction, multiview video sequence, manually constructed dinosaur model, keyframe animation, Deformable models, Face, Training, Bones, Data models, Geometry, Animation, CCA regression., Detail-preserving deformation, controllable skinning, learning from sparse examples
Yue Qi, Ling Zhao, KangKang Yin, Haoda Huang, Yizhou Yu and Xin Tong, "Detail-Preserving Controllable Deformation from Sparse Examples," in IEEE Transactions on Visualization & Computer Graphics, vol. 18, no. , pp. 1215-1227, 2012.