EUVIMEDEUVIMED entdecken
Crossref

A mutually boosting dual sensor computational camera for high quality dark videography

Yuxiao Cheng, Runzhao Yang, Zhihong Zhang, Jinli Suo, Qionghai Dai

Information Fusion · 2023-05 · 93 · 429-440

DOI: 10.1016/j.inffus.2023.01.013 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information Fusion, 2023-05. Verfasst von Yuxiao Cheng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: Ministry of Science and Technology of the People's Republic of China, Natural Science Foundation of Beijing Municipality, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Videos captured under low light conditions suffer from severe noise. A variety of efforts have been devoted to image/video noise suppression and made large progress. However, in extremely dark scenarios, extensive photon starvation would hamper precise noise modeling. Instead, developing an imaging system collecting more photons is a more effective way for high-quality video capture under low illuminations. In this paper, we propose to build a dual-sensor camera to additionally collect the photons in NIR wavelength, and make use of the correlation between RGB and near-infrared (NIR) spectrum to perform high-quality reconstruction from noisy dark video pairs. In hardware, we build a compact dual-sensor camera capturing RGB and NIR videos simultaneously. Computationally, we propose a dual-channel multi-frame attention network (DCMAN) utilizing spatial-temporal-spectral priors to reconstruct the low-light RGB and NIR videos. In addition, we build a high-quality paired RGB and NIR video dataset, based on which the approach can be applied to different sensors easily by training the DCMAN model with simulated noisy input following a physical-process-based CMOS noise model. Both experiments on synthetic and real videos validate the performance of this compact dual-sensor camera design and the corresponding reconstruction algorithm in dark videography.

Förderung

  • Ministry of Science and Technology of the People's Republic of China
  • Natural Science Foundation of Beijing Municipality
  • National Natural Science Foundation of China

Zitieren

APA

Cheng, Y., Yang, R., Zhang, Z., Suo, J., & Dai, Q. (2023). A mutually boosting dual sensor computational camera for high quality dark videography. Information Fusion, 93, 429-440. https://doi.org/10.1016/j.inffus.2023.01.013

Vancouver

Cheng Y, Yang R, Zhang Z, Suo J, Dai Q. A mutually boosting dual sensor computational camera for high quality dark videography. Information Fusion. 2023;93:429-440. doi:10.1016/j.inffus.2023.01.013

BibTeX
@article{Cheng2023,
  author = {Cheng, Yuxiao and Yang, Runzhao and Zhang, Zhihong and Suo, Jinli and Dai, Qionghai},
  title = {A mutually boosting dual sensor computational camera for high quality dark videography},
  journal = {Information Fusion},
  year = {2023},
  volume = {93},
  pages = {429--440},
  doi = {10.1016/j.inffus.2023.01.013}
}
Kostenlos starten →