Abstract: PURPOSE: Multi-illuminant based color constancy (MCC) is a quite challenging task. In this paper, we proposed a novel model motivated by the bottom-up and top-down mechanisms of human visual system (HVS) to estimate the spatially varying illumination in a scene.
METHODS: The motivation for bottom-up based estimation is from our finding that the bright and dark parts in a scene play different roles in encoding illuminants. However, the pure bottom-up processing is difficult to handle the color shift of large colorful objects. Thus, we further introduce a top-down constraint inspired by the findings in visual psychophysics, in which high level information (e.g., the prior of light source colors) plays a key role in visual color constancy. In order to implement the top-down hypothesis, we simply learn a color mapping between the illuminant distribution estimated by bottom-up processing and the ground truth maps provided by the dataset.
RESULTS: We evaluated our model on four datasets and the results show that our method obtains very competitive performance compared to the state-of-the-art MCC algorithms. Moreover, the robustness of our model is more tangible considering that our results were obtained using the same parameters for all the datasets or the parameters of our model were learned from the inputs, that is, mimicking how HVS operates.
CONCLUSIONS: The computational results in our model implies that the prior of illuminant plays an important role in keeping the robust CC performance for HVS. However, what's the neural substrate that may encode this information are not clear. Hence, our future work will concentrate on developing the physiological methods such as fMRI to further exploit the cortical basis of CC.

Key words: color vision, color constancy, fMRI, biologically inspired computer vision