End-to-End Denoising of Dark Burst Images using Recurrent Fully Convolutional Networks

Lan Ma, Di Zhao, Songnan Li, Dahai Yu

2020

Abstract

When taking photos in dim-light environments, due to the small amount of light entering, the shot images are usually extremely dark, with a great deal of noise, and the color cannot reflect real-world color. Under this condition, the traditional methods used for single image denoising have always failed to be effective. One common idea is to take multiple frames of the same scene to enhance the signal-to-noise ratio. This paper proposes a recurrent fully convolutional network (RFCN) to process burst photos taken under extremely low-light conditions, and to obtain denoised images with improved brightness. Our model maps raw burst images directly to sRGB outputs, either to produce a best image or to generate a multi-frame denoised image sequence. This process has proven to be capable of accomplishing the low-level task of denoising, as well as the high-level task of color correction and enhancement, all of which is end-to-end processing through our network. Our method has achieved better results than state-of-the-art methods. In addition, we have applied the model trained by one type of camera without fine-tuning on photos captured by different cameras and have obtained similar end-to-end enhancements.

Paper Citation

in Harvard Style

Ma L., Zhao D., Li S. and Yu D. (2020). End-to-End Denoising of Dark Burst Images using Recurrent Fully Convolutional Networks. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 189-196. DOI: 10.5220/0008895901890196

in Bibtex Style

@conference{visapp20,
author={Lan Ma and Di Zhao and Songnan Li and Dahai Yu},
title={End-to-End Denoising of Dark Burst Images using Recurrent Fully Convolutional Networks},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP},
year={2020},
pages={189-196},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008895901890196},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP
TI - End-to-End Denoising of Dark Burst Images using Recurrent Fully Convolutional Networks
SN - 978-989-758-402-2
AU - Ma L.
AU - Zhao D.
AU - Li S.
AU - Yu D.
PY - 2020
SP - 189
EP - 196
DO - 10.5220/0008895901890196
PB - SciTePress