We present a universal statistical model for texture images in the context of an overcomplete complex wavelet transform. The model is parameterized by a set of statistics computed ...
This paper describes a method allowing the automatic multi-texturing and simulation of surface imperfections based on a cellular network. In this representation, networks of conne...
We present a method for retexturing non-rigid objects from a single viewpoint. Without reconstructing 3D geometry, we create realistic video with shape cues at two scales. At a coa...
Abstract. This paper addresses the problem of probabilistically modeling 3D human motion for synthesis and tracking. Given the high dimensional nature of human motion, learning an ...
The class of all natural images is an extremely small fraction of all possible images. Some of the structure of natural images can be modeled statistically, revealing striking reg...
Erik Reinhard, Peter Shirley, Michael Ashikhmin, T...