Color Constancy Using CNNs
This work addresses color constancy for computer vision applications, but it is incremental as it builds on existing CNN approaches with a specific network structure.
The authors tackled the problem of scene illumination estimation by developing a CNN that processes image patches directly in the spatial domain, eliminating the need for hand-crafted features, and achieved state-of-the-art performance on a standard RAW image dataset.
In this work we describe a Convolutional Neural Network (CNN) to accurately predict the scene illumination. Taking image patches as input, the CNN works in the spatial domain without using hand-crafted features that are employed by most previous methods. The network consists of one convolutional layer with max pooling, one fully connected layer and three output nodes. Within the network structure, feature learning and regression are integrated into one optimization process, which leads to a more effective model for estimating scene illumination. This approach achieves state-of-the-art performance on a standard dataset of RAW images. Preliminary experiments on images with spatially varying illumination demonstrate the stability of the local illuminant estimation ability of our CNN.