Recovering 3D geometry from a single view of an object is an important and challenging problem in computer vision. Previous methods mainly focus on one specific class of objects ...
This paper proposes a methodology to estimate the correlation model between a pair of images that are given under the form of linear measurements. We consider an image pair whose ...
Sparse representations over redundant dictionaries offer an efficient paradigm for signal representation. Recently block-sparsity has been put forward as a prior condition for so...
This paper presents a Markov Random Field (MRF)-based approach for depth map super-resolution and enhancement. Given a low-resolution or moderate quality depth map, we study the p...
We propose a kernelized maximal-figure-of-merit (MFoM) learning approach to efficiently training a nonlinear model using subspace distance minimization. In particular, a fixed,...