SDE-AWB: a Generic Solution for 2nd International Illumination Estimation Challenge
This work addresses illumination estimation for computer vision applications, representing an incremental improvement by combining existing components for a competition-specific task.
The authors tackled the problem of illumination estimation in images by proposing SDE-AWB, a neural network-based solution that achieved first place in indoor and two-illuminant tracks and second place in the general track of the 2nd International Illumination Estimation Challenge.
We propose a neural network-based solution for three different tracks of 2nd International Illumination Estimation Challenge (chromaticity.iitp.ru). Our method is built on pre-trained Squeeze-Net backbone, differential 2D chroma histogram layer and a shallow MLP utilizing Exif information. By combining semantic feature, color feature and Exif metadata, the resulting method -- SDE-AWB -- obtains 1st place in both indoor and two-illuminant tracks and 2nd place in general track.