G
Giannis Chantas
Researcher at University of Ioannina
Publications - 27
Citations - 510
Giannis Chantas is an academic researcher from University of Ioannina. The author has contributed to research in topics: Bayesian inference & Prior probability. The author has an hindex of 8, co-authored 26 publications receiving 459 citations. Previous affiliations of Giannis Chantas include Information Technology Institute & Aristotle University of Thessaloniki.
Papers
More filters
Journal ArticleDOI
Variational Bayesian Image Restoration With a Product of Spatially Weighted Total Variation Image Priors
TL;DR: A new image prior is introduced and used in image restoration based on products of spatially weighted total variations (TV) which provides this prior with the flexibility to better capture local image features than previous TV based priors.
Journal ArticleDOI
Variational Bayesian Image Restoration Based on a Product of $t$ -Distributions Image Prior
TL;DR: A new Bayesian algorithm is proposed for the image restoration problem that bypasses this difficulty of finding the normalization constant of image priors in closed form.
Journal ArticleDOI
Bayesian Restoration Using a New Nonstationary Edge-Preserving Image Prior
TL;DR: A class of image restoration algorithms based on the Bayesian approach and a new hierarchical spatially adaptive image prior that preserves edges and generalizes the on/off (binary) line process idea used in previous image priors within the context of Markov random fields (MRFs).
Journal ArticleDOI
Super-Resolution Based on Fast Registration and Maximum a Posteriori Reconstruction
TL;DR: An efficient two-step reconstruction methodology that includes first an initial registration using only the low-resolution degraded observations and a fast iterative algorithm implemented in the discrete Fourier transform domain in which the restoration, interpolation and the registration subtasks of this problem are preformed simultaneously.
Journal ArticleDOI
Variational-Bayes Optical Flow
TL;DR: A variational Bayesian approach of the Horn-Schunck optical flow method is presented, where the motion vectors are considered to be spatially varying Student’s t-distributed unobserved random variables, which may substitute the standard algorithm in the initialization of more sophisticated optical flow schemes.