Computer Graphics Laboratory ETH Zurich

ETH

Fast and Stable Color Balancing for Images and Augmented Reality

T. Oskam, A. Hornung, R. Sumner, M. Gross

3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT) (Zurich, Switzerland, October 13-15, 2012), pp. 49 - 56
[Abstract] [BibTeX] [PDF]

Abstract

This paper addresses the problem of globally balancing colors between images. The input to our algorithm is a sparse set of desired color correspondences between a source and a target image. The global color space transformation problem is then solved by computing a smooth vector field in CIE Lab color space that maps the gamut of the source to that of the target. We employ normalized radial basis functions for which we compute optimized shape parameters based on the input images, allowing for more faithful and flexible color matching compared to existing RBF-, regression- or histogram-based techniques. Furthermore, we show how the basic per-image matching can be efficiently and robustly extended to the temporal domain using RANSAC-based correspondence classification. Besides interactive color balancing for images, these properties render our method extremely useful for automatic, consistent embedding of synthetic graphics in video, as required by applications such as augmented reality.

@INPROCEEDINGS{6374976,
author={Oskam, T. and Hornung, A. and Sumner, R.W. and Gross, M.},
booktitle={3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), 2012 Second International Conference on},
title={Fast and Stable Color Balancing for Images and Augmented Reality},
year={2012},
month={Oct},
pages={49-56},
keywords={augmented reality;image classification;image colour analysis;image matching;radial basis function networks;video signal processing;CIE Lab color space;RANSAC-based correspondence classification;RBF-based techniques;augmented reality;color matching;fast color balancing;global color space transformation problem;globally balancing colors;histogram-based techniques;images;interactive color balancing;normalized radial basis functions;optimized shape parameters;regression-based techniques;smooth vector field;stable color balancing;synthetic graphics;temporal domain;video;Augmented reality;Cameras;Image color analysis;Interpolation;Robustness;Target tracking;Vectors;augmented reality;color balancing;radial basis functions},
doi={10.1109/3DIMPVT.2012.36},}
[Download BibTeX]

Downloads

Download Paper
[PDF]