Generative Models for Multi-Illumination Color Constancy

TL;DR

This paper introduces a physics-inspired generative adversarial network approach for multi-illumination color constancy, addressing dataset scarcity and outperforming state-of-the-art methods in multi-illumination scenarios.

Contribution

It proposes a novel GAN-based method with a multi-illumination data augmentation technique for improved color constancy under multiple light sources.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effective multi-illumination data augmentation improves model robustness.

Demonstrates the viability of GANs for multi-illumination color correction.

Abstract

In this paper, the aim is multi-illumination color constancy. However, most of the existing color constancy methods are designed for single light sources. Furthermore, datasets for learning multiple illumination color constancy are largely missing. We propose a seed (physics driven) based multi-illumination color constancy method. GANs are exploited to model the illumination estimation problem as an image-to-image domain translation problem. Additionally, a novel multi-illumination data augmentation method is proposed. Experiments on single and multi-illumination datasets show that our methods outperform sota methods.