Advances in Environmental Protection, Год журнала: 2024, Номер 14(04), С. 1026 - 1033
Опубликована: Янв. 1, 2024
Язык: Английский
Advances in Environmental Protection, Год журнала: 2024, Номер 14(04), С. 1026 - 1033
Опубликована: Янв. 1, 2024
Язык: Английский
Building and Environment, Год журнала: 2025, Номер unknown, С. 112744 - 112744
Опубликована: Фев. 1, 2025
Язык: Английский
Процитировано
0Remote Sensing, Год журнала: 2025, Номер 17(7), С. 1165 - 1165
Опубликована: Март 25, 2025
In mining environments, ensuring image authenticity is critical for safety monitoring. However, current low-light enhancement methods often fail to balance optimization and fidelity, resulting in suboptimal quality. Additionally, existing models trained on general datasets do not meet the unique demands of which feature challenging lighting conditions. To address this, we propose Mining Environment Transformer (MEFormer), a high-fidelity restoration network with efficient computational performance. MEFormer incorporates an innovative cross-scale fusion architecture, facilitates enhanced across multiple scales. We also present Low-Light (MELOL) new dataset that captures specific conditions found filling gap available data. Experiments public MELOL demonstrate achieves 0.05 increase SSIM, PSNR above 25, LPIPS score 0.15. The model processes 10,000 128 × images just 2.8 s using Nvidia H100 GPU.
Язык: Английский
Процитировано
0Journal of Wind Engineering and Industrial Aerodynamics, Год журнала: 2025, Номер 262, С. 106096 - 106096
Опубликована: Апрель 10, 2025
Язык: Английский
Процитировано
0Advances in Environmental Protection, Год журнала: 2024, Номер 14(04), С. 1026 - 1033
Опубликована: Янв. 1, 2024
Язык: Английский
Процитировано
0