Time-Aware Auto White Balance in Mobile Photography
This addresses color correction issues for mobile photography users, but it is incremental as it builds on existing AWB methods by adding metadata.
The paper tackles the problem of auto white balance in mobile photography by proposing a lightweight illuminant estimation method that incorporates contextual metadata like timestamp and geolocation, achieving results that match or surpass larger models on a new dataset of 3,224 smartphone images.
Cameras rely on auto white balance (AWB) to correct undesirable color casts caused by scene illumination and the camera's spectral sensitivity. This is typically achieved using an illuminant estimator that determines the global color cast solely from the color information in the camera's raw sensor image. Mobile devices provide valuable additional metadata-such as capture timestamp and geolocation-that offers strong contextual clues to help narrow down the possible illumination solutions. This paper proposes a lightweight illuminant estimation method that incorporates such contextual metadata, along with additional capture information and image colors, into a compact model (~5K parameters), achieving promising results, matching or surpassing larger models. To validate our method, we introduce a dataset of 3,224 smartphone images with contextual metadata collected at various times of day and under diverse lighting conditions. The dataset includes ground-truth illuminant colors, determined using a color chart, and user-preferred illuminants validated through a user study, providing a comprehensive benchmark for AWB evaluation.