Deep Retinex Network for Estimating Illumination Colors with Self-Supervised Learning

TL;DR

This paper introduces a self-supervised deep Retinex network that effectively decomposes images into reflectance and shading, enabling improved illumination estimation and white-balance adjustment without requiring labeled data.

Contribution

A novel Retinex network considering all three reflectance-shading consistencies and trained with self-supervised learning using pseudo-images, advancing illumination decomposition methods.

Findings

Successfully decomposes images into reflectance and shading components.

Enables effective white-balance adjustment.

Operates without labeled training data.

Abstract

We propose a novel Retinex image-decomposition network that can be trained in a self-supervised manner. The Retinex image-decomposition aims to decompose an image into illumination-invariant and illumination-variant components, referred to as "reflectance" and "shading," respectively. Although there are three consistencies that the reflectance and shading should satisfy, most conventional work considers only one or two of the consistencies. For this reason, the three consistencies are considered in the proposed network. In addition, by using generated pseudo-images for training, the proposed network can be trained with self-supervised learning. Experimental results show that our network can decompose images into reflectance and shading components. Furthermore, it is shown that the proposed network can be used for white-balance adjustment.