التفاصيل البيبلوغرافية
| العنوان: |
Multi-Band NIR-Based Low-Light Image Enhancement via Dual-Teacher Cross Attention |
| المؤلفون: |
Jeong-Hyeok Park, Dong-Min Lee, Tae-Hyeon Kim, Tae-Sung Park, Jong-Ok Kim |
| المصدر: |
IEEE Access, Vol 12, Pp 111360-111370 (2024) |
| بيانات النشر: |
IEEE, 2024. |
| سنة النشر: |
2024 |
| المجموعة: |
LCC:Electrical engineering. Electronics. Nuclear engineering |
| مصطلحات موضوعية: |
Retinex-theory, cross-attention, multi-band NIR, knowledge distillation, Electrical engineering. Electronics. Nuclear engineering, TK1-9971 |
| الوصف: |
Low-light images often lack visibility and information, and traditional methods of adjusting camera sensitivity and exposure time can result in visual quality degradation. In this paper, we propose a low-light enhancement method that utilizes two novel approaches to address these issues. The first approach involves using multi-band NIR (Near Infra-red) to preserve structural components, while a transformer-based cross-attention module efficiently calculates the correlation between NIR and RGB for effective fusion. The second approach involves implementing dual-teacher knowledge distillation, where normal- and mid-light teacher networks transfer low-light enhancement knowledge to the student. Our proposed method produces better color and detail restoration results than existing methods, particularly in ultra low-light environments. We also provide our own datasets for two different low-light conditions, enabling wide evaluations and ablation studies. |
| نوع الوثيقة: |
article |
| وصف الملف: |
electronic resource |
| اللغة: |
English |
| تدمد: |
2169-3536 |
| Relation: |
https://ieeexplore.ieee.org/document/10630798/; https://doaj.org/toc/2169-3536 |
| DOI: |
10.1109/ACCESS.2024.3440410 |
| URL الوصول: |
https://doaj.org/article/57acae8510514c5d914696aacd2b985a |
| رقم الانضمام: |
edsdoj.57acae8510514c5d914696aacd2b985a |
| قاعدة البيانات: |
Directory of Open Access Journals |
Full Text Finder