Minimum Error Rate Training is the algorithm for log-linear model parameter training most used in state-of-the-art Statistical Machine Translation systems. In its original formula...
This paper presents a novel optimization framework for estimating the static or dynamic surfaces with details. The proposed method uses dense depths from a structuredlight system ...
Limited by the regular grids in computing, many modelling approaches (e.g., field-based methods) sample 3D shape insensitive to sharp features therefore exhibit aliasing errors, b...
We present a new approachto interactive modeling of freeform surfaces. Instead of a fixed mesh of control points, the model presented to the user is that of an infinitely malleabl...
Traditional approaches for modeling a closed manifold surface with either regular tensor-product or triangular splines (defined over an open planar domain) require decomposing th...