E
Egon C. Pasztor
Researcher at Mitsubishi Electric Research Laboratories
Publications - 12
Citations - 5178
Egon C. Pasztor is an academic researcher from Mitsubishi Electric Research Laboratories. The author has contributed to research in topics: Markov chain & Node (networking). The author has an hindex of 9, co-authored 12 publications receiving 4931 citations. Previous affiliations of Egon C. Pasztor include Massachusetts Institute of Technology & Mitsubishi Electric.
Papers
More filters
Journal ArticleDOI
Example-based super-resolution
TL;DR: This work built on another training-based super- resolution algorithm and developed a faster and simpler algorithm for one-pass super-resolution that requires only a nearest-neighbor search in the training set for a vector derived from each patch of local image data.
Journal ArticleDOI
Learning Low-Level Vision
TL;DR: A learning-based method for low-level vision problems—estimating scenes from images with Bayesian belief propagation, applied to the “super-resolution” problem (estimating high frequency details from a low-resolution image), showing good results.
Proceedings ArticleDOI
Learning low-level vision
TL;DR: This work shows a learning-based method for low-level vision problems-estimating scenes from images with a Markov network, and applies VISTA to the "super-resolution" problem (estimating high frequency details from a low-resolution image), showing good results.
Journal ArticleDOI
Hyperscore: a graphical sketchpad for novice composers
TL;DR: The Hyperscore graphical computer-assisted composition system for users with limited or no musical training takes freehand drawing as input, letting users literally sketch their pieces.
Proceedings Article
Learning to Estimate Scenes from Images
TL;DR: From synthetic data, the relationship between image and scene patches is modeled, and between a scene patch and neighboring scene patches, and this yields an efficient method to form low-level scene interpretations.