R
Ruben Verhack
Researcher at Ghent University
Publications - 13
Citations - 148
Ruben Verhack is an academic researcher from Ghent University. The author has contributed to research in topics: Pixel & JPEG. The author has an hindex of 5, co-authored 13 publications receiving 104 citations. Previous affiliations of Ruben Verhack include Technical University of Berlin.
Papers
More filters
Proceedings ArticleDOI
Steered mixture-of-experts for light field coding, depth estimation, and processing
TL;DR: The proposed framework, called Steered Mixture-of-Experts (SMoE), enables a multitude of processing tasks on light fields using a single unified Bayesian model that takes into account different regions of the scene, their edges, and their development along the spatial and disparity dimensions.
Journal ArticleDOI
Steered Mixture-of-Experts for Light Field Images and Video: Representation and Coding
TL;DR: A novel coding framework for higher-dimensional image modalities, called Steered Mixture-of-Experts (SMoE), which performs comparable to the state of the art for low-to-mid range bitrates with respect to subjective visual quality of 4-D LF images and 5- D LF video.
Proceedings ArticleDOI
A universal image coding approach using sparse steered Mixture-of-Experts regression
TL;DR: This work introduces a sparse Mixture-of-Experts regression approach for coding images in the pixel domain and attempts to design the coder and decoder “universal”, such that MPEG-7-like low- and mid-level descriptors are an integral part of the coded representation.
Proceedings ArticleDOI
Video representation and coding using a sparse steered mixture-of-experts network
TL;DR: A novel approach for video compression that explores spatial as well as temporal redundancies over sequences of many frames in a unified framework and developed a sparse Steered Mixture-of-Experts (SMoE) regression network for coding video in the pixel domain.
Proceedings ArticleDOI
Hierarchical Learning of Sparse Image Representations Using Steered Mixture-of-Experts
TL;DR: A novel estimation method based on Hidden Markov Random Fields is introduced taking spatial dependencies of neighboring pixels into account combined with a tree-structured splitting strategy that outperforms state-of-the-art techniques using only one robust parameter set.