Truong D. Nguyen

We don’t have enough information about this author to calculate their statistics. If you think this is an error let us know.
Learn More
Disparity estimation is a key component in 3D image processing , yet dense estimation is a computationally intensive task. In this paper, we propose to estimate the dense disparities from a small set of spatial measurements. Observing that disparity maps mainly contain contours and smooth regions, we formulate the problem as a sparse reconstruction problem(More)
Lemma 1. The derivatives of the Gaussian functions g(t; σ) = 1 √ 2πσ 2 e − t 2 2σ 2 are g ′ (t; σ) = 1 √ 2πσ 2 (− t σ 2 e − t 2 2σ 2) and g ′′ (t; σ) = 1 √ 2πσ 2 (t 2 σ 4 − 1 σ 2)e − t 2 2σ 2. Scale-space axiom requires that there is no enhancement to the local maximum and local minimum [1]. Therefore, the derivative must be normalized. Defining the mth(More)
  • 1