ReflectNet -- A Generative Adversarial Method for Single Image Reflection Suppression

TL;DR

ReflectNet introduces a generative adversarial approach with a novel data generation model to effectively remove reflections from single images, outperforming existing methods in quality metrics.

Contribution

The paper presents a new reflection removal method combining context understanding and adversarial training, along with a complex synthetic data generation model.

Findings

Outperforms state-of-the-art methods in PSNR and SSIM

Uses a novel data generation model for training

Effective single image reflection suppression

Abstract

Taking pictures through glass windows almost always produces undesired reflections that degrade the quality of the photo. The ill-posed nature of the reflection removal problem reached the attention of many researchers for more than decades. The main challenge of this problem is the lack of real training data and the necessity of generating realistic synthetic data. In this paper, we proposed a single image reflection removal method based on context understanding modules and adversarial training to efficiently restore the transmission layer without reflection. We also propose a complex data generation model in order to create a large training set with various type of reflections. Our proposed reflection removal method outperforms state-of-the-art methods in terms of PSNR and SSIM on the SIR benchmark dataset.