Reflection Removal Using
Recurrent Polarization-to-Polarization Network
Wenjiao Bian,
Yusuke Monno,
and Masatoshi Okutomi
Tokyo Institute of Technology
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2024)
[paper],
[supp]
Abstract & Network
This paper addresses reflection removal, which is the task of separating reflection components from a captured image and deriving the image with only transmission components. Considering that the existence of the reflection changes the polarization state of a scene, some existing methods have exploited polarized images for reflection removal. While these methods apply polarized images as the inputs, they predict the reflection and the transmission directly as non-polarized intensity images. In contrast, we propose a polarization-to-polarization approach that applies polarized images as the inputs and predicts “polarized” reflection and transmission images using two sequential networks to facilitate the separation task by utilizing the interrelated polarization information between the reflection and the transmission. We further adopt a recurrent framework, where the predicted reflection and transmission images are used to iteratively refine each other. Experimental results on a public dataset demonstrate that our method outperforms other state-of-the-art methods.
Method Overview
|
|
Different input-output models for the reflection removal task: (a) Both the input and the output of standard single-image methods are intensity images. (b) Existing polarization-based methods apply polarized images only to the input. (c) Our proposed polarization-to-polarization approach predicts the output reflection and transmission as polarized images as well. |
Our Results
Quantitative comparisons on Lei et al. dataset. * : Non-learning-based methods. †: Learning-based methods using pre-trained models.
Publication
Reflection Removal Using Recurrent Polarization-to-Polarization Network [PDF]
Wenjiao Bian,
Yusuke Monno,
and Masatoshi Okutomi
Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)
Contact
Wenjiao Bian: wbian[at]ok.sc.e.titech.ac.jp
Yusuke Monno: ymonno[at]ok.sc.e.titech.ac.jp
Masatoshi Okutomi: mxo[at]sc.e.titech.ac.jp