Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements

Kaixuan Wei, Jiaolong Yang, Ying Fu, David Wipf, Hua Huang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 8178-8187

Abstract


Removing undesirable reflections from a single image captured through a glass window is of practical importance to visual computing systems. Although state-of-the-art methods can obtain decent results in certain situations, performance declines significantly when tackling more general real-world cases. These failures stem from the intrinsic difficulty of single image reflection removal -- the fundamental ill-posedness of the problem, and the insufficiency of densely-labeled training data needed for resolving this ambiguity within learning-based neural network pipelines. In this paper, we address these issues by exploiting targeted network enhancements and the novel use of misaligned data. For the former, we augment a baseline network architecture by embedding context encoding modules that are capable of leveraging high-level contextual clues to reduce indeterminacy within areas containing strong reflections. For the latter, we introduce an alignment-invariant loss function that facilitates exploiting misaligned real-world training data that is much easier to collect. Experimental results collectively show that our method outperforms the state-of-the-art with aligned data, and that significant improvements are possible when using additional misaligned data.

Related Material


[pdf]
[bibtex]
@InProceedings{Wei_2019_CVPR,
author = {Wei, Kaixuan and Yang, Jiaolong and Fu, Ying and Wipf, David and Huang, Hua},
title = {Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}