Polarized Reflection Removal With Perfect Alignment in the Wild

Chenyang Lei, Xuhua Huang, Mengdi Zhang, Qiong Yan, Wenxiu Sun, Qifeng Chen; The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 1750-1758

Abstract


We present a novel formulation to removing reflection from polarized images in the wild. We first identify the misalignment issues of existing reflection removal datasets where the collected reflection-free images are not perfectly aligned with input mixed images due to glass refraction. Then we build a new dataset with more than 100 types of glass in which obtained transmission images are perfectly aligned with input mixed images. Second, capitalizing on the special relationship between reflection and polarized light, we propose a polarized reflection removal model with a two-stage architecture. In addition, we design a novel perceptual NCC loss that can improve the performance of reflection removal and general image decomposition tasks. We conduct extensive experiments, and results suggest that our model outperforms state-of-the-art methods on reflection removal.

Related Material


[pdf]
[bibtex]
@InProceedings{Lei_2020_CVPR,
author = {Lei, Chenyang and Huang, Xuhua and Zhang, Mengdi and Yan, Qiong and Sun, Wenxiu and Chen, Qifeng},
title = {Polarized Reflection Removal With Perfect Alignment in the Wild},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}