Color Constancy by Reweighting Image Feature Maps
This work addresses color constancy in computer vision, which is important for applications like photography and robotics, but appears incremental as it builds on existing deep learning and assumption-based approaches.
The paper tackles illuminant color estimation for computational color constancy by proposing a framework that combines deep learning with interpretable assumption-based models, achieving comparable accuracy to prior state-of-the-art deep learning models while using a more compact model size and lower computational cost.
In this study, a novel illuminant color estimation framework is proposed for computational color constancy, which incorporates the high representational capacity of deep-learning-based models and the great interpretability of assumption-based models. The well-designed building block, feature map reweight unit (ReWU), helps to achieve comparative accuracy on benchmark datasets with respect to prior state-of-the-art deep learning based models while requiring more compact model size and cheaper computational cost. In addition to local color estimation, a confidence estimation branch is also included such that the model is able to simultaneously produce point estimate and its uncertainty estimate, which provides useful clues for local estimates aggregation and multiple illumination estimation. The source code and the dataset have been made available at https://github.com/QiuJueqin/Reweight-CC.