Polarization-Aware Low-Light Image Enhancement
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (3) · 3742-3750
DOI: 10.1609/aaai.v37i3.25486 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Chu Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref).
Abstract (Originalsprache)
Polarization-based vision algorithms have found uses in various applications since polarization provides additional physical constraints. However, in low-light conditions, their performance would be severely degenerated since the captured polarized images could be noisy, leading to noticeable degradation in the degree of polarization (DoP) and the angle of polarization (AoP). Existing low-light image enhancement methods cannot handle the polarized images well since they operate in the intensity domain, without effectively exploiting the information provided by polarization. In this paper, we propose a Stokes-domain enhancement pipeline along with a dual-branch neural network to handle the problem in a polarization-aware manner. Two application scenarios (reflection removal and shape from polarization) are presented to show how our enhancement can improve their results.
Zitieren
APA
Zhou, C., Teng, M., Lyu, Y., Li, S., Xu, C., & Shi, B. (2023). Polarization-Aware Low-Light Image Enhancement. Proceedings of the AAAI Conference on Artificial Intelligence, 37(3), 3742-3750. https://doi.org/10.1609/aaai.v37i3.25486
Vancouver
Zhou C, Teng M, Lyu Y, Li S, Xu C, Shi B. Polarization-Aware Low-Light Image Enhancement. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(3):3742-3750. doi:10.1609/aaai.v37i3.25486
BibTeX
@article{Zhou2023,
author = {Zhou, Chu and Teng, Minggui and Lyu, Youwei and Li, Si and Xu, Chao and Shi, Boxin},
title = {Polarization-Aware Low-Light Image Enhancement},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {3},
pages = {3742--3750},
doi = {10.1609/aaai.v37i3.25486}
}
EUVIMED