We address the problem of label assignment in computer
vision: given a novel 3-D or 2-D scene, we wish to assign a
unique label to every site (voxel, pixel, superpixel, etc.). To...
Daniel Munoz, James A. Bagnell, Martial Hebert, Ni...
Correspondence problems are of great importance in
computer vision. They appear as subtasks in many applications
such as object recognition, merging partial 3D reconstructions
a...
Based on scaling laws describing the statistical structure
of turbulent motion across scales, we propose a multiscale
and non-parametric regularizer for optic-flow estimation.
R...
Patrick H´eas, Etienne M´emin, Dominique Heitz, ...
Recovering the three-dimensional (3D) object shape lies as an unresolved and active research topic on the crosssection of computer vision, photogrammetry and bioinformatics. Altho...
Invariant feature descriptors such as SIFT and GLOH have been demonstrated to be very robust for image matching and visual recognition. However, such descriptors are generally par...