DIF-LIM: A Dual Information Flow Network for Low-Light Image Enhancement DOI
Mengjie Qin, Rong Yang,

Zheyuan Lin

и другие.

2021 IEEE International Conference on Robotics and Biomimetics (ROBIO), Год журнала: 2023, Номер unknown, С. 1 - 6

Опубликована: Дек. 4, 2023

Low-light image enhancement (LIE) aims to enhance contrast and recover fine details for images captured in low-light conditions. However, the limitations of using a single manually defined priors lead inadequate information limited adaptability, resulting failure reveal effectively. To tackle this problem, we propose an unsupervised dual flow LIE model that learns adaptive from pairs. The is based on assumption can be learned pairs images. Moreover, simple self+supervised designed perform feature processing original input further avoid suboptimal model. As result, our exhibits superior performance task compared other algorithms. improved network adaptability

Язык: Английский

LFDT-Fusion: A Latent Feature-guided Diffusion Transformer Model for general image fusion DOI
Bo Yang, Zhaohui Jiang, Dong Pan

и другие.

Information Fusion, Год журнала: 2024, Номер 113, С. 102639 - 102639

Опубликована: Авг. 16, 2024

Язык: Английский

Процитировано

8

Detail-aware near infrared and visible fusion with multi-order hyper-Laplacian priors DOI
Bo Yang, Zhaohui Jiang, Dong Pan

и другие.

Information Fusion, Год журнала: 2023, Номер 99, С. 101851 - 101851

Опубликована: Май 23, 2023

Язык: Английский

Процитировано

11

A low-light image enhancement framework based on hybrid multiscale decomposition and adaptive brightness adjustment model DOI
Yizheng Lang, Yunsheng Qian

Optics & Laser Technology, Год журнала: 2025, Номер 185, С. 112621 - 112621

Опубликована: Фев. 18, 2025

Язык: Английский

Процитировано

0

Detail-preserving noise suppression post-processing for low-light image enhancement DOI
Lei He, Zunhui Yi, Chaoyang Chen

и другие.

Displays, Год журнала: 2024, Номер 83, С. 102738 - 102738

Опубликована: Май 9, 2024

Язык: Английский

Процитировано

3

Semantic-agnostic progressive subtractive network for image manipulation detection and localization DOI

Dengyun Xu,

Xuanjing Shen, Zenan Shi

и другие.

Neurocomputing, Год журнала: 2023, Номер 543, С. 126263 - 126263

Опубликована: Апрель 27, 2023

Язык: Английский

Процитировано

5

Multimodal image fusion based on diffusion model DOI
Bo Yang, Zhaohui Jiang, Dong Pan

и другие.

Опубликована: Июнь 28, 2024

Процитировано

0

A saturation-light enhancement method for low-light image via atmospheric scattering model DOI
Yu Wang, Jinyu Li, Chuncheng Zhang

и другие.

Optics and Lasers in Engineering, Год журнала: 2024, Номер 183, С. 108488 - 108488

Опубликована: Авг. 13, 2024

Язык: Английский

Процитировано

0

RMANet: Refined-mixed attention network for progressive low-light image enhancement DOI
Ke Chen, Kaibing Zhang, Feifei Pang

и другие.

Signal Processing, Год журнала: 2024, Номер 227, С. 109689 - 109689

Опубликована: Сен. 6, 2024

Язык: Английский

Процитировано

0

A customized mask signal connected components labelingalgorithm DOI
Rui Yang, Cong Chen, Xiaojun Qian

и другие.

Signal Processing, Год журнала: 2024, Номер 230, С. 109845 - 109845

Опубликована: Дек. 9, 2024

Язык: Английский

Процитировано

0

DIF-LIM: A Dual Information Flow Network for Low-Light Image Enhancement DOI
Mengjie Qin, Rong Yang,

Zheyuan Lin

и другие.

2021 IEEE International Conference on Robotics and Biomimetics (ROBIO), Год журнала: 2023, Номер unknown, С. 1 - 6

Опубликована: Дек. 4, 2023

Low-light image enhancement (LIE) aims to enhance contrast and recover fine details for images captured in low-light conditions. However, the limitations of using a single manually defined priors lead inadequate information limited adaptability, resulting failure reveal effectively. To tackle this problem, we propose an unsupervised dual flow LIE model that learns adaptive from pairs. The is based on assumption can be learned pairs images. Moreover, simple self+supervised designed perform feature processing original input further avoid suboptimal model. As result, our exhibits superior performance task compared other algorithms. improved network adaptability

Язык: Английский

Процитировано

0