ReflectNet -- A Generative Adversarial Method for Single Image Reflection Suppression
This addresses the issue of degraded photo quality due to reflections for photographers and computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of removing undesired reflections from single images taken through glass, proposing a method that uses context understanding modules and adversarial training to restore the transmission layer, and it outperforms state-of-the-art methods on the SIR benchmark dataset in terms of PSNR and SSIM metrics.
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.