This paper studies the problem of 3D non-rigid shape and motion recovery from a monocular video sequence, under the degenerate deformations. The shape of a deformable object is re...
We describe a probabilistic framework for recognizing human activities in monocular video based on simple silhouette observations in this paper. The methodology combines kernel pr...
In this paper we present a novel approach to estimate and analyze 3D uid structure and motion of clouds from multi-spectrum 2D cloud image sequences. Accurate cloud-top structure ...
We present a closed form solution to the nonrigid shape and motion (NRSM) problem from point correspondences in multiple perspective uncalibrated views. Under the assumption that t...
—We present a generative model and inference algorithm for 3D nonrigid object tracking. The model, which we call G-flow, enables the joint inference of 3D position, orientation, ...