Removing the undesired reflections from images taken through the glass is of broad application to various computer vision tasks. Non-learning based methods utilize different handcrafted priors such as the separable sparse gradients caused by different levels of blurs, which often fail due to their limited description capability to the properties of real-world reflections. In this paper, we propose the Concurrent Reflection Removal Network (CRRN) to tackle this problem in a unified framework. Our proposed network integrates image appearance information and multi-scale gradient information with human perception inspired loss function, and is trained on a new dataset with 3250 reflection images taken under diverse real-world scenes. Extensive experiments on a public benchmark dataset show that the proposed method performs favorably against state-of-the-art methods.
@article{arxiv.1805.11802,
title = {CRRN: Multi-Scale Guided Concurrent Reflection Removal Network},
author = {Renjie Wan and Boxin Shi and Ling-Yu Duan and Ah-Hwee Tan and Alex C. Kot},
journal= {arXiv preprint arXiv:1805.11802},
year = {2018}
}