Color Constancy by Reweighting Image Feature Maps

TL;DR

This paper introduces a deep learning framework for color constancy that combines high representational capacity with interpretability, featuring a reweighting mechanism and uncertainty estimation, achieving competitive accuracy with reduced complexity.

Contribution

It presents a novel feature map reweighting unit and an uncertainty estimation branch, enhancing accuracy and interpretability in color constancy models.

Findings

Achieves comparable accuracy to state-of-the-art models

Uses fewer parameters and lower computational cost

Provides uncertainty estimates for local and multiple illuminant scenarios

Abstract

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.