Probabilistic Color Constancy
This addresses color constancy in computer vision, but it is incremental as it builds on existing methods with a new weighting approach.
The paper tackles the problem of estimating scene illumination for color constancy by proposing an unsupervised method that weights image regions based on color similarity and darkness, achieving competitive performance on the INTEL-TAU dataset.
In this paper, we propose a novel unsupervised color constancy method, called Probabilistic Color Constancy (PCC). We define a framework for estimating the illumination of a scene by weighting the contribution of different image regions using a graph-based representation of the image. To estimate the weight of each (super-)pixel, we rely on two assumptions: (Super-)pixels with similar colors contribute similarly and darker (super-)pixels contribute less. The resulting system has one global optimum solution. The proposed method achieves competitive performance, compared to the state-of-the-art, on INTEL-TAU dataset.