Publication Type

Journal Article

Version

acceptedVersion

Publication Date

6-2019

Abstract

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 a network with the feature-sharing strategy to tackle this problem in a cooperative and unified framework, by integrating image context information and the multi-scale gradient information. To remove the strong reflections existed in some local regions, we propose a statistic loss by considering the gradient level statistics between the background and reflections. Our network is trained on a new dataset with 3250 reflection images taken under diverse real-world scenes. Experiments on a public benchmark dataset show that the proposed method performs favorably against state-of-the-art methods.

Keywords

Reflection removal, deep learning, statistic loss, cooperative framework

Discipline

Programming Languages and Compilers | Software Engineering

Research Areas

Data Science and Engineering

Publication

IEEE Transactions on Pattern Analysis and Machine Intelligence

First Page

1

Last Page

14

ISSN

0162-8828

Identifier

10.1109/TPAMI.2019.2921574

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Additional URL

https://doi.org/10.1109/TPAMI.2019.2921574

Share

COinS