Image Shadow Removal Using Paired Region Illumination Transfer

Abstract

In this paper we present a novel method for shadow detection and removal in single images. Instead of a single Gaussian distribution in the shadow detection stage, it is assumed as a Gaussian Mixture Shadow Model (GMSM) which parameters are estimated by model learning. In addition to considering individual regions separately, we predict relative illumination conditions between the shadow regions and non-shadow regions. The shadow image is recovered by relighting each pixel based on our paired lighting model. The experiment results confirm the effectiveness of our proposed method.