Formulating Camera-Adaptive Color Constancy as a Few-shot Meta-Learning Problem

TL;DR

This paper introduces a meta-learning approach for camera-adaptive color constancy that quickly adapts to new cameras with minimal data, improving generalization across devices and reducing data collection efforts.

Contribution

It formulates color constancy as few-shot regression tasks within a meta-learning framework, enabling rapid adaptation to unseen cameras with limited samples.

Findings

Achieves competitive accuracy with fewer camera-specific samples

Demonstrates robustness across diverse datasets and cameras

Reduces data annotation time for new sensors

Abstract

Digital camera pipelines employ color constancy methods to estimate an unknown scene illuminant, in order to re-illuminate images as if they were acquired under an achromatic light source. Fully-supervised learning approaches exhibit state-of-the-art estimation accuracy with camera-specific labelled training imagery. Resulting models typically suffer from domain gaps and fail to generalise across imaging devices. In this work, we propose a new approach that affords fast adaptation to previously unseen cameras, and robustness to changes in capture device by leveraging annotated samples across different cameras and datasets. We present a general approach that utilizes the concept of color temperature to frame color constancy as a set of distinct, homogeneous few-shot regression tasks, each associated with an intuitive physical meaning. We integrate this novel formulation within a meta-learning framework, enabling fast generalisation to previously unseen cameras using only handfuls of camera specific training samples. Consequently, the time spent for data collection and annotation substantially diminishes in practice whenever a new sensor is used. To quantify this gain, we evaluate our pipeline on three publicly available datasets comprising 12 different cameras and diverse scene content. Our approach delivers competitive results both qualitatively and quantitatively while requiring a small fraction of the camera-specific samples compared to standard approaches.