Custom color enhancements by statistical learning

We consider the problem of automatically learning color enhancements from a small set of sample color pairs, and then describing the enhancement by a three-dimensional look-up-table that can be stored and implemented as an ICC profile. We propose a new method for automatically learning a neighborhood for local statistical learning methods such as local linear regression, and show that this leads to relatively accurate descriptions of the desired color transformation and results in images that appear smooth and have natural depth of detail. In a previous work we showed that learning arbitrary color enhancements could result in colored specular highlights, causing images to look unnatural. We show that this can be solved by adding a sample that maps white to white.