Color prediction in image coding using Steered Mixture-of-Experts
Ruben Verhack, Simon Van De Keer, Glenn Van Wallendael, Thomas Sikora, Peter Lambert
Abstract
We propose a novel approach for modeling and coding color in images and video. Luminance is linearly correlated with chrominance locally, as such we can predict color given the luma value. Using the Steered Mixture-of-Experts (SMoE) approach, the image is viewed as a stochastic process over 5 random variables including the 2-D pixel locations, 1 luminance and 2 chrominance values. We model this process as a continuous joint density function by fitting a K-modal 5-D Gaussian Mixture Model (GMM). As such, the chroma values are predicted as the expectation of the conditional density. To validate, the technique was integrated within JPEG showing PSNR gains in the lower bitrate regions. A deeper analysis of the tolerance of the activation function is given through recycling color models in video sequences, yielding a high quality reconstruction over a considerable range of frames.
BibTeX
@inproceedings{icassp2017_colorpredictioni,
title = {Color prediction in image coding using Steered Mixture-of-Experts},
author = {Ruben Verhack and Simon Van De Keer and Glenn Van Wallendael and Thomas Sikora and Peter Lambert},
booktitle = {ICASSP 2017},
year = {2017}
}