Color Constancy by GANs: An Experimental Survey

TL;DR

This paper surveys the use of Generative Adversarial Networks (GANs) for color constancy, analyzing various architectures through extensive experiments and providing design recommendations based on dataset and application specifics.

Contribution

It offers the first comprehensive experimental survey of GAN-based methods for color constancy, guiding future architecture design choices.

Findings

Different GAN architectures vary in effectiveness for color constancy

Recommendations improve the design of CC-GANs for specific datasets

Experimental results highlight key factors influencing performance

Abstract

In this paper, we formulate the color constancy task as an image-to-image translation problem using GANs. By conducting a large set of experiments on different datasets, an experimental survey is provided on the use of different types of GANs to solve for color constancy i.e. CC-GANs (Color Constancy GANs). Based on the experimental review, recommendations are given for the design of CC-GAN architectures based on different criteria, circumstances and datasets.