Sensor-Independent Illumination Estimation for DNN Models

TL;DR

This paper introduces a sensor-independent framework for illuminant estimation in DNNs, enabling models to generalize across different camera sensors without retraining.

Contribution

A novel sensor-independent working space is learned, allowing a single DNN to perform well across various sensors by canonicalizing RGB values.

Findings

Achieves comparable performance to sensor-specific models

Retains linear properties of raw-RGB space

Reduces need for retraining with new sensors

Abstract

While modern deep neural networks (DNNs) achieve state-of-the-art results for illuminant estimation, it is currently necessary to train a separate DNN for each type of camera sensor. This means when a camera manufacturer uses a new sensor, it is necessary to retrain an existing DNN model with training images captured by the new sensor. This paper addresses this problem by introducing a novel sensor-independent illuminant estimation framework. Our method learns a sensor-independent working space that can be used to canonicalize the RGB values of any arbitrary camera sensor. Our learned space retains the linear property of the original sensor raw-RGB space and allows unseen camera sensors to be used on a single DNN model trained on this working space. We demonstrate the effectiveness of this approach on several different camera sensors and show it provides performance on par with state-of-the-art methods that were trained per sensor.