Image composition with color harmonization

Abstract

Image composition is a very important technique in computer generated imagery (CGI). Besides some factors such as contrast, texture, noise that affect the quality of the composition, color harmony between fore- and background is also an important issue that should be carefully dealt with. However, in the previous image composition techniques, the color harmony between fore- and background is seldom considered. In this paper, an optimization method is presented to deal with the color harmonization problem that used in image composition. A cost function is derived from the observation of the local smoothness of the hue values. And the image is harmonized by minimizing the cost function. A new matching function is presented to select the best matching harmonic schemes, and a new component based pre-harmonization strategy is also presented to preserve the hue distribution of the harmonized images. Our approach overcomes several shortcomings of the existed color harmonization methods. We validate the performance of the method and demonstrate its effectiveness in a variety of experiments.