We present a generalization of the nonnegative matrix factorization (NMF), where a multilayer generative network with nonnegative weights is used to approximate the observed nonne...
The work proposes a hierarchical architecture for learning amic scenes at various levels of knowledge abstraction. The raw visual information is processed at different stages to g...
A technique for performing progressive mesh-based motion estimation in a layered fashion is presented. Motion compensation based on image warping provides a block prediction free ...
We propose a layered facial simulation model for skin aging with wrinkles, which includes muscle, connective tissue and skin layer. Our aim is to simulate relevant facial animatio...
This paper deals with the problem of estimating multiple motions at points where these motions are overlaid. We present a new approach that is based on block matching and can deal...