LUMINA-Net: Low-light Upgrade through Multi-stage Illumination and Noise Adaptation Network for Image Enhancement

TL;DR

LUMINA-Net is an unsupervised deep learning framework that enhances low-light images by adaptively adjusting illumination and reducing noise through multi-stage modules, outperforming existing methods on standard datasets.

Contribution

The paper introduces LUMINA-Net, a novel unsupervised network with multi-stage illumination and noise reduction modules for improved low-light image enhancement.

Findings

Outperforms state-of-the-art methods on LOL and SICE datasets.

Effectively reduces noise while enhancing image details.

Achieves higher PSNR, SSIM, and LPIPS scores.

Abstract

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.