Reflection Removal Using Recurrent Polarization-to-Polarization Network
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929258479222784 |
|---|---|
| author | Bian, Wenjiao Monno, Yusuke Okutomi, Masatoshi |
| author_facet | Bian, Wenjiao Monno, Yusuke Okutomi, Masatoshi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18178 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reflection Removal Using Recurrent Polarization-to-Polarization Network Bian, Wenjiao Monno, Yusuke Okutomi, Masatoshi Computer Vision and Pattern Recognition 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. |
| title | Reflection Removal Using Recurrent Polarization-to-Polarization Network |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.18178 |