پیوندهای مفید
آمار
| تعداد نشریات | 9 |
| تعداد شمارهها | 452 |
| تعداد مقالات | 5,750 |
| تعداد مشاهده مقاله | 8,249,962 |
| تعداد دریافت فایل اصل مقاله | 6,766,791 |
Attention-Guided Dehazing: A New Architecture with Low-Level and Multi-Level Channel Attention | ||
| AUT Journal of Electrical Engineering | ||
| دوره 58، شماره 2، تیر 2026، صفحه 383-404 اصل مقاله (1.45 M) | ||
| نوع مقاله: Research Article | ||
| شناسه دیجیتال (DOI): 10.22060/eej.2026.24359.5691 | ||
| نویسندگان | ||
| Hossein Noori* ؛ Mohammad Hossein Gholizadeh؛ Gholamreza Memarzadeh | ||
| Assistant Professor, Department of Electrical Engineering, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran | ||
| چکیده | ||
| Single-image dehazing has become increasingly vital in recent years due to its foundational role in enhancing high-level vision tasks such as object detection, remote sensing, and autonomous driving. While numerous deep learning-based approaches have been proposed, many still fall short in fully preserving image details and capturing complex haze patterns. In this paper, a novel end-to-end architecture for single-image dehazing is presented that addresses key limitations of existing methods. The proposed network integrates two innovative modules: the Low-Level Feature Attention (LLFA) module, which emphasizes the retention of fine-grained details often lost in deeper layers, and the Multi-Level Channel Attention (MLCA) module, which dynamically fuses low- and high-level features to improve the network’s representational capacity. By leveraging these complementary modules across multiple resolution scales, the architecture achieves more effective feature extraction and superior haze removal. Extensive experiments on both synthetic and real-world datasets demonstrate that our method consistently outperforms state-of-the-art algorithms in both qualitative visual clarity and quantitative evaluation metrics. The results confirm the robustness and efficiency of the proposed approach in producing clean, detail-rich dehazed images. | ||
| کلیدواژهها | ||
| Defogging/dehazing؛ feature attention؛ deep learning؛ channel attention؛ convolutional neural networks | ||
|
آمار تعداد مشاهده مقاله: 72 تعداد دریافت فایل اصل مقاله: 44 |
||