The Community for Technology Leaders
Green Image
This paper describes methods for recovering time-varying shape and motion of non-rigid 3D objects from uncalibrated 2D point tracks. For example, given a video recording of a talking person, we would like to estimate the 3D shape of the face at each instant, and learn a model of facial deformation. Time-varying shape is modeled as a rigid transformation combined with a non-rigid deformation. Reconstruction is ill-posed if arbitrary deformations are allowed, and thus additional assumptions about deformations are required. We first suggest restricting shapes to lie within a low-dimensional subspace, and describe estimation algorithms. However, this restriction alone is insufficient to constrain reconstruction. To address these problems, we propose a reconstruction method using a Probabilistic Principal Components Analysis (PPCA) shape model, and an estimation algorithm that simultaneously estimates 3D shape and motion for each instant, learns the PPCA model parameters, and robustly fills-in missing data points. We then extend the model to model temporal dynamics in object shape, allowing the algorithm to robustly handle severe cases of missing data.
Motion, Shape, Machine learning, 3D/stereo scene analysis
Lorenzo Torresani, Aaron Hertzmann, Chris Bregler, "Nonrigid Structure-from-Motion: Estimating Shape and Motion with Hierarchical Priors", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 30, no. , pp. 878-892, May 2008, doi:10.1109/TPAMI.2007.70752
79 ms
(Ver 3.3 (11022016))