LUMINA-Net: Low-light Upgrade through Multi-stage Illumination and Noise Adaptation Network for Image Enhancement
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912484454039552 |
|---|---|
| author | Siddiqua, Namrah Suneung, Kim Lee, Seong-Whan |
| author_facet | Siddiqua, Namrah Suneung, Kim Lee, Seong-Whan |
| contents | Low-light image enhancement (LLIE) is a crucial task in computer vision aimed at enhancing the visual fidelity of images captured under low-illumination conditions. Conventional methods frequently struggle with noise, overexposure, and color distortion, leading to significant image quality degradation. To address these challenges, we propose LUMINA-Net, an unsupervised deep learning framework that learns adaptive priors from low-light image pairs by integrating multi-stage illumination and reflectance modules. To assist the Retinex decomposition, inappropriate features in the raw image can be removed using a simple self-supervised mechanism. First, the illumination module intelligently adjusts brightness and contrast while preserving intricate textural details. Second, the reflectance module incorporates a noise reduction mechanism that leverages spatial attention and channel-wise feature refinement to mitigate noise contamination. Through extensive experiments on LOL and SICE datasets, evaluated using PSNR, SSIM, and LPIPS metrics, LUMINA-Net surpasses state-of-the-art methods, demonstrating its efficacy in low-light image enhancement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15186 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LUMINA-Net: Low-light Upgrade through Multi-stage Illumination and Noise Adaptation Network for Image Enhancement Siddiqua, Namrah Suneung, Kim Lee, Seong-Whan Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Low-light image enhancement (LLIE) is a crucial task in computer vision aimed at enhancing the visual fidelity of images captured under low-illumination conditions. Conventional methods frequently struggle with noise, overexposure, and color distortion, leading to significant image quality degradation. To address these challenges, we propose LUMINA-Net, an unsupervised deep learning framework that learns adaptive priors from low-light image pairs by integrating multi-stage illumination and reflectance modules. To assist the Retinex decomposition, inappropriate features in the raw image can be removed using a simple self-supervised mechanism. First, the illumination module intelligently adjusts brightness and contrast while preserving intricate textural details. Second, the reflectance module incorporates a noise reduction mechanism that leverages spatial attention and channel-wise feature refinement to mitigate noise contamination. Through extensive experiments on LOL and SICE datasets, evaluated using PSNR, SSIM, and LPIPS metrics, LUMINA-Net surpasses state-of-the-art methods, demonstrating its efficacy in low-light image enhancement. |
| title | LUMINA-Net: Low-light Upgrade through Multi-stage Illumination and Noise Adaptation Network for Image Enhancement |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.15186 |