TL;DR本文提出了一个基于物理的多光源颜色恒常性方法,利用 GAN 将照明估计问题建模为图像到图像域转换问题,并提出了一种新型的多照明数据增强方法,实验证明该方法优于现有工作。
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