Shape and pose parameter estimation of 3D multi-part objects

This paper presents an analysis-by-image-synthesis framework of shape and pose estimation of 3D multi-part objects, whose purpose is to map objects in the real world into virtual environments. In general, complex 3D multi-part objects cause serious self-occlusion and non-rigid motion. To deal with the occlusion among them, we employ both multiple calibrated cameras and time-varying sequences, since there is enough information to estimate the parameters in the sensory data. In our framework, to minimize the error between the selected measurements and the estimated model parameters, we proceed model fitting process based on proper numerical analysis.