MetadataShow full item record
AbstractMorphing between 3D objects is a fundamental technique in computer graphics. Traditional methods of shape morphing focus on establishing meaningful correspondences and finding smooth interpolation between shapes. Such methods however only take geometric information as input and thus cannot in general avoid producing unnatural interpolation, in particular for large-scale deformations. This paper proposes a novel data-driven approach for shape morphing. Given a database with various models belonging to the same category, we treat them as data samples in the plausible deformation space. These models are then clustered to form local shape spaces of plausible deformations. We use a simple metric to reasonably represent the closeness between pairs of models. Given source and target models, the morphing problem is casted as a global optimization problem of finding a minimal distance path within the local shape spaces connecting these models. Under the guidance of intermediate models in the path, an extended as-rigid-as-possible interpolation is used to produce the final morphing. By exploiting the knowledge of plausible models, our approach produces realistic morphing for challenging cases as demonstrated by various examples in the paper. © 2013 The Eurographics Association and Blackwell Publishing Ltd.
CitationGao L, Lai Y-K, Huang Q-X, Hu S-M (2013) A Data-Driven Approach to Realistic Shape Morphing. Computer Graphics Forum 32: 449–457. Available: http://dx.doi.org/10.1111/cgf.12065.
SponsorsWe would like to thank Jia-Jia Sun for his help with experiments. This work was supported by the National Basic Research Project of China (Project Number 2011CB302202), the Natural Science Foundation of China (Project Number 61120106007), the National High Technology Research and Development Program of China (Project Number 2012AA011801) and National Significant Science and Technology Program (Project Number 2012ZX01039001-003). Qi-Xing Huang is supported by NSF grants FODA-VA (Project Number 808515) and CCF (Project Number 1011228), the KAUST Academic Excellence Alliance, and a Google Research Award.
JournalComputer Graphics Forum