Abstract: Proper white balance is essential in photographs to eliminate color casts due to illumination. The single-light case is hard to solve automatically but relatively easy for humans. Unfortunately, many scenes contain multiple light sources such as an indoor scene with a window, or when a flash is used in a tungsten-lit room. The light color can then vary on a per-pixel basis and the problem becomes challenging at best, even with advanced image editing tools.
We propose a solution to the ill-posed mixed light white balance problem, based on user guidance. Users scribble on a few regions that should have the same color, indicate one or more regions of neutral color (i.e., white or gray), and select regions where the current color looks correct. We first expand the provided scribble groups to more regions using pixel similarity and a robust voting scheme. We formulate the spatially varying white balance problem as a sparse data interpolation problem in which the user scribbles and their extensions form constraints. We demonstrate that our approach can produce satisfying results on a variety of scenes with intuitive scribbles and without any knowledge about the lights.
We would like to thank the anonymous reviewers for their constructive comments. Ivaylo Boyadzhiev and Kavita Bala acknowledge funding from NSF (CAREER 1041534 and IIS 1011919) and Adobe. Frédo Durand acknowledges funding from Quanta, NSF grant 0964004, and gifts from Adobe and Cognex. We thank A. Bousseau and M. Ebner for helping us comparing to their systems.
| Page maintained by Ivaylo Boyadzhiev
Last update: September 2012