Projects

In this paper, we consider the problem of animation reconstruction, i.e., the reconstruction of shape and motion of a deformable object from dynamic 3D scanner data, without using user provided template models. Unlike pre- vious work that addressed this problem, we do not rely on locally conver- gent optimization but present a system that can handle fast motion, tem- porally disrupted input, and can correctly match objects that disappear for extended time periods in acquisition holes due to occlusion. Our approach is motivated by cartography: We first estimate a few landmark correspon- dences, which are extended to a dense matching and then used to recon- struct geometry and motion. We propose a number of algorithmic building blocks: a scheme for tracking landmarks in temporally coherent and inco- herent data, an algorithm for robust estimation of dense correspondences under topological noise, and the integration of local matching techniques to refine the result. We describe and evaluate the individual components and propose a complete animation reconstruction pipeline based on these ideas. We evaluate our method on a number of standard benchmark data sets and show that we can obtain correct reconstructions in situations where other techniques fail completely or require additional user guidance such as a template model.