Feature enhancement network architecture for low-light image

Author:

Jin Zihao1,Liu Zhiyong1

Affiliation:

1. Harbin Institute of Technology

Abstract

Abstract

Limitations such as shooting equipment and environmental conditions can significantly impact the quality of captured images. Image enhancement, a crucial task in computer vision, aims to improve the overall or local characteristics of an image, particularly its brightness and contrast, to enhance the visual effect. The Retinex model has proven effective for low-light image enhancement. In this work, we propose a novel feature enhancement network architecture that combines the Retinex model with deep learning. The network comprises three main components: a decomposition network for image decomposition, an enhancement network for the luminance component obtained from decomposition, and a denoising network for the reflection component. The network’s learning process relies primarily on key constraints, including the consistency of the reflection component and the smoothness of the luminance component post-image decomposition. We conducted experiments on synthetic datasets involving real environments and processed images, and the results demonstrate that our method strikes a good balance between reducing parameters and maintaining high-quality image enhancement compared to other algorithms.

Publisher

Springer Science and Business Media LLC

Reference50 articles.

1. The neural basis of visual body perception[J];Peelen MV;Nat. Rev. Neurosci.,2007

2. Neuropsychological mechanisms of visual face and body perception[J];Minnebusch DA;Neurosci. Biobehavioral Reviews,2009

3. Cognitive fit: An empirical study of information acquisition[J];Vessey I;Inform. Syst. Res.,1991

4. Computer vision for image-based transcriptomics[J];Stoeger T;Methods,2015

5. Temby, P., Ryder, C., Vozzo, A., et al.: Sharp shooting in fuzzy fields: effects of image clarity in virtual environments[C]//Proceedings of the 10th Simulation, Technology, and Training Conference. (2005)

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3