SDE-AWB: a Generic Solution for 2nd International Illumination Estimation Challenge

TL;DR

SDE-AWB is a neural network approach that combines semantic, color, and metadata features to excel in illumination estimation, winning multiple challenge tracks.

Contribution

It introduces a novel combination of pre-trained Squeeze-Net, chroma histograms, and Exif data for illumination estimation.

Findings

Achieved 1st place in indoor and two-illuminant tracks

Secured 2nd place in the general track

Demonstrated effectiveness of multi-modal feature integration

Abstract

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.