Dong Qu

Dong Qu


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 April 2025 in ISA Transactions
Verified
Journal Article
Closed access
GCGuan-Qun Chen
Guan-Qun Chen
WXWen-Bo Xie
Wen-Bo Xie
DQDong Qu
Dong Qu
YPYan Peng
Yan Peng

2 August 2019
Verified
Book Chapter
Closed access
PDF file
JCJunjie Chen
Junjie Chen
YYYang Yang
Yang Yang
XJXingang Jiang
Xingang Jiang
XHXiaolong He
Xiaolong He
SXShaorong Xie
Shaorong Xie
DQDong Qu
Dong Qu

27 November 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ZSZhihua Shen
Zhihua Shen
CWCaiju Wang
Caiju Wang
FLFei Li
Fei Li
JLJinshuo Liang
Jinshuo Liang
XLXiaomao Li
Xiaomao Li
DQDong Qu
Dong Qu
Unsupervised low-light image enhancement methods have gained attention and shown improvement with low data dependence. However, the lack of a ground truth presents challenges, notably in pronounced noise and color bias. This paper proposes a Self-Guided Pixel-wise Calibration method to overcome associated issues by leveraging inherent features from the input as a self-guide. Specifically, a Pixel-wise Guided Filter is introduced to decrease noise, utilizing a low-light image for guidance and deep features as regularization maps. Additionally, a Color Correction Module is introduced to enhance saturation by adjusting the shadow threshold. Finally, a pixel-wise exposure control loss is formalized to optimize overall naturalness by adjusting brightness to a well-exposedness map from the low-light image. Extensive experiments demonstrate that our method outperforms many state-of-the-art methods, producing enhanced results with fewer distortions across various real-world image enhancement tasks.

1 October 2025
Verified
Book Chapter
Closed access
PDF file
YZYonghang Zheng
Yonghang Zheng
YPYan Peng
Yan Peng
DQDong Qu
Dong Qu