Approximate Cross Channel Color Mapping from Sparse Color Correspondences

Abstract

We propose a color mapping method that compensates color differences between images having a common semantic content such as multiple views of a scene taken from different viewpoints. A so-called color mapping model is usually estimated from color correspondences selected from those images. In this work, we introduce a color mapping that model color change in two steps: first, nonlinear, channel-wise mapping; second, linear, cross-channel mapping. Additionally, unlike many state of the art methods, we estimate the model from sparse matches and do not require dense geometric correspondences. We show that well known cross-channel color change can be estimated from sparse color correspondence. Quantitative and visual benchmark tests show good performance compared to recent methods in literature.

Colour Mapping: A Review of Recent Methods, Extensions and Applications

“…Ideally, the results of a colour mapping method can be assessed through comparisons with a ground truth. In cases where the pair of input images are similar in structure, it is possible to produce image sets that provide a ground truth [FST13]. Further, quality metrics can be employed to compare the result with the original input image [SDZL09,TD11].…”

“…In the case of stereo or multiple views, Faridul et al [FST12,FST13] provide a quantitative evaluation framework. Here, the idea is to capture ground truth colour along with the test images to be corrected.…”

“…Instead of changing the illumination, the same principle can be extended to model other causes of variation in colour between images such as varying white balance. Faridul et al [FST13] report colour mapping results in such case of varying white balance where the ground truth allows direct quantitative evaluation. Although this type of controlled input can be used to evaluate colour mapping methods, ground truth images can only be acquired when the input and reference images represent the same scene under different viewpoints.…”

“…For set C, where the images are taken from our previous work [FST13], we used a studio lighted by led panels from Elation (TVL2000). We controlled these light sources by a MAYA plug-in.…”

Histogram-Based Color Transfer for Image Stitching

“…Color transfer is also known as color correction, color mapping or color alignment in the literature [2][3][4][5][6][7]. This kind of technique is aimed to transfer the color style of a reference image to a test image.…”