| Autor: |
Yangjun Xiang, Gengsheng Hu, Mei Chen, Mahmoud Emam |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
IEEE Access, Vol 12, Pp 105674-105685 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2169-3536 |
| DOI: |
10.1109/ACCESS.2024.3434531 |
| Popis: |
Low-light images captured at night often suffer from improper exposure, color distortion, and noise, which degrades the image quality and have a negative influence on subsequent applications. Many existing deep learning-based methods enhance low-light images through spatial domain, which may sacrifice the original image information. In this paper, we put forward a deep learning network for enhancing low-light images based on wavelet transform. We utilize the wavelet transform to divide the image into various frequency scales and then analyze the frequency characteristics of different low-light images in the wavelet domain. The proposed network comprises a low-frequency restoration subnet and high-frequency reconstruction subnet that uses an optimal coefficient of wavelet decomposition to construct a frequency pyramid. Furthermore, we utilized different attention mechanisms to extract frequency information from different images, gradually restoring the brightness information and details of low-light images. Additionally, we utilized a self-constructed multi-scale exposure low-light image dataset for training. Numerous experiments on publicly accessible datasets and our established dataset show that the proposed approach quantitatively and qualitatively surpasses state-of-the-art approaches, particularly for real and complex low-light scenarios. Furthermore, our method produces better visual effects than others and performs well in real-time and real-word downstream vision tasks. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
