Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2019

Abstract

Due to the lack of paired data, the training of image reflection removal relies heavily on synthesizing reflection images. However, existing methods model reflection as a linear combination model, which cannot fully simulate the real-world scenarios. In this paper, we inject non-linearity into reflection removal from two aspects. First, instead of synthesizing reflection with a fixed combination factor or kernel, we propose to synthesize reflection images by predicting a non-linear alpha blending mask. This enables a free combination of different blurry kernels, leading to a controllable and diverse reflection synthesis. Second, we design a cascaded network for reflection removal with three tasks: predicting the transmission layer, reflection layer, and the non-linear alpha blending mask. The former two tasks are the fundamental outputs, while the latter one being the side output of the network. This side output, on the other hand, making the training a closed loop, so that the separated transmission and reflection layers can be recombined together for training with a reconstruction loss. Extensive quantitative and qualitative experiments demonstrate the proposed synthesis and removal approaches outperforms state-of-the-art methods on two standard benchmarks, as well as in real-world scenarios.

Keywords

Computer science, Computers, Electrical engineering, Pattern recognition, Software engineering

Discipline

Artificial Intelligence and Robotics | Electrical and Computer Engineering | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

First Page

3771

Last Page

3779

ISBN

9781728132945

Identifier

10.1109/CVPR.2019.00389

Publisher

IEEE

City or Country

USA

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/CVPR.2019.00389

Download

Share

COinS