期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 23, 期 -, 页码 4272-4284出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2020.3039361
关键词
Laplace equations; Image restoration; Lighting; Image enhancement; Visualization; Image color analysis; Histograms; Low-light image enhancement; Laplacian pyramid; deep-stacked laplacian restorer (DSLR); decomposition-based scheme
资金
- National Research Foundation of Korea (NRF) - Korea government (MSIT) [2020R1F1A1068080]
- National Research Foundation of Korea [2020R1F1A1068080] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
The paper introduces a novel method for low-light image enhancement by leveraging the useful properties of the Laplacian pyramid in image and feature spaces. The proposed deep stacked Laplacian restorer (DSLR) is capable of separately recovering global illumination and local details and progressively combining them in the image space.
Various images captured in complicated lighting conditions often suffer from deterioration of the image quality. Such poor quality not only dissatisfies the user expectation but also may lead to a significant performance drop in many applications. In this paper, anovel method for low-light image enhancement is proposed by leveraging useful propertiesof the Laplacian pyramid both in image and feature spaces. Specifically, the proposed method, so-called a deep stacked Laplacian restorer (DSLR), is capable of separately recovering the global illumination and local details from the original input, and progressively combining them in the image space. Moreover, the Laplacian pyramid defined in the feature space makes such recovering processes more efficient based on abundant connectionsof higher-order residuals in a multiscale structure. This decomposition-based scheme is fairly desirable for learning the highly nonlinear relation between degraded images and their enhanced results. Experimental results on various datasets demonstrate that the proposed DSLR outperforms state-of-the-art methods. The code and model are publicly available at: https://github.com/SeokjaeLIM/DSLR-release.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据