DARK: Denoising, Amplification, Restoration Kit

TL;DR

This paper presents DARK, a lightweight neural network framework that significantly improves low-light image quality by effectively reducing noise, restoring details, and maintaining natural colors, suitable for real-time applications.

Contribution

The paper introduces a novel, efficient CNN-based model inspired by Retinex theory that enhances low-light images with minimal computational overhead, outperforming existing methods.

Findings

Outperforms existing low-light enhancement methods in quality.

Maintains low computational complexity suitable for real-time use.

Effectively reduces noise and color distortion in challenging lighting conditions.

Abstract

This paper introduces a novel lightweight computational framework for enhancing images under low-light conditions, utilizing advanced machine learning and convolutional neural networks (CNNs). Traditional enhancement techniques often fail to adequately address issues like noise, color distortion, and detail loss in challenging lighting environments. Our approach leverages insights from the Retinex theory and recent advances in image restoration networks to develop a streamlined model that efficiently processes illumination components and integrates context-sensitive enhancements through optimized convolutional blocks. This results in significantly improved image clarity and color fidelity, while avoiding over-enhancement and unnatural color shifts. Crucially, our model is designed to be lightweight, ensuring low computational demand and suitability for real-time applications on standard consumer hardware. Performance evaluations confirm that our model not only surpasses existing methods in enhancing low-light images but also maintains a minimal computational footprint.