Sensor-Independent Illumination Estimation for DNN Models
This addresses a practical issue for camera manufacturers by reducing retraining efforts when using new sensors, though it is incremental as it builds on existing DNN methods.
The paper tackles the problem of needing separate DNN models for each camera sensor in illuminant estimation by introducing a sensor-independent framework that canonicalizes RGB values, achieving performance on par with per-sensor state-of-the-art methods.
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.