We present a closed-form solution to the problem of recovering
the 3D shape of a non-rigid potentially stretchable
surface from 3D-to-2D correspondences. In other words,
we can ...
Francesc Moreno-Noguer (Institut de Robotica i Inf...
We present a manifold learning approach to dimensionality
reduction that explicitly models the manifold as a mapping
from low to high dimensional space. The manifold is
represen...
Given a dense set of imperfect normals obtained by photometric stereo or shape from shading, this paper presents an optimization algorithm which alternately optimizes until conver...
Two new techniques are proposed to improve stereo matching performance in this work. First, to address the disparity discontinuity problem in occluded regions, we present a dispar...