Deep gradual flash fusion for low-light enhancement
- Authors
- Kim, Jae-Woo; Ryu, Je-Ho; Kim, Jong-Ok
- Issue Date
- 10월-2020
- Publisher
- ACADEMIC PRESS INC ELSEVIER SCIENCE
- Keywords
- Image fusion; Flash fusion; Pseudo multi-exposure; Auto-encoder; GAN; Low light enhancement
- Citation
- JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, v.72
- Indexed
- SCIE
SCOPUS
- Journal Title
- JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
- Volume
- 72
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/52647
- DOI
- 10.1016/j.jvcir.2020.102903
- ISSN
- 1047-3203
- Abstract
- In this paper, we propose gradual flash fusion, a new imaging concept that enables acquisition of pseudo multi-exposure images in a passive manner. This means that our gradual flash capture does not require any user-side manipulation (taking multiple shots or varying camera settings). Continuous high-speed capture naturally contains different intensities of flash in a single shooting. The captured gradual flash images, containing different information of the same scene, are fused to generate higher-quality images, especially in a low light scenario. For gradual flash fusion, we use a Generative Adversarial Network (GAN) based approach, where the generator is a tailored convolutional Auto-Encoder for image fusion. For the training, we build a custom dataset comprising gradual flash images and corresponding ground truths. This enables supervised learning, unlike most conventional image fusion studies. Experimental results demonstrate that gradual flash fusion achieves artifact-free and noise-free results resembling ground truth, owing to supervised adversarial fusion.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.