Image colour transfer aims to alter the colours of one image (source) to mimic the appearance and colour palette of another one (target).
It is useful to remove unwanted colour cast or getting perceptual visual compatibility for image comparison, for creating colour consistent panoramic images and 3D texture maps. In computer graphics, synthetic images can borrow another´s image look and gain realism.
Reinhard et al. introduced a simple but robust method for colour transfer [1] and an image example is illustrated in Figure 1. Their approach is to use image statistical properties, such as mean and standard deviation, and apply one image characteristics to the other.
Fig. 1 An example of applying image colour transfer [1]. (left) target image . (centre) source image. (right) image result of applying colour transfer [1] on the source image to borrow colour characteristics of the target image.
To alter the colours of one image pixel must be done by altering all colours in tandem and this task is optimally performed in a colour space with minimal correlation between channels, such that the result of the colour transfer operation does not have unwanted cross-channel artifacts.
Bibliography
[1] E. Reinhard, M. Adhikhmin, B. Gooch and P. Shirley, "Color transfer between images," in IEEE Computer Graphics and Applications, vol. 21, no. 5, pp. 34-41, July-Aug. 2001, doi: 10.1109/38.946629.