Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement

TL;DR

This paper introduces LASQ, a novel unsupervised hierarchical learning framework that models luminance transitions as power-law distributions, improving low-light image enhancement by capturing natural luminance dynamics without relying on paired references.

Contribution

LASQ reformulates low-light image enhancement as a statistical sampling over luminance distributions, incorporating a diffusion process for unsupervised learning of luminance transitions, which enhances adaptability and generalization.

Findings

Outperforms existing methods on domain-specific datasets.

Achieves better generalization across non-reference datasets.

Effectively models luminance dynamics using power-law distributions.

Abstract

Low-light image enhancement (LLIE) faces persistent challenges in balancing reconstruction fidelity with cross-scenario generalization. While existing methods predominantly focus on deterministic pixel-level mappings between paired low/normal-light images, they often neglect the continuous physical process of luminance transitions in real-world environments, leading to performance drop when normal-light references are unavailable. Inspired by empirical analysis of natural luminance dynamics revealing power-law distributed intensity transitions, this paper introduces Luminance-Aware Statistical Quantification (LASQ), a novel framework that reformulates LLIE as a statistical sampling process over hierarchical luminance distributions. Our LASQ re-conceptualizes luminance transition as a power-law distribution in intensity coordinate space that can be approximated by stratified power functions, therefore, replacing deterministic mappings with probabilistic sampling over continuous luminance layers. A diffusion forward process is designed to autonomously discover optimal transition paths between luminance layers, achieving unsupervised distribution emulation without normal-light references. In this way, it considerably improves the performance in practical situations, enabling more adaptable and versatile light restoration. This framework is also readily applicable to cases with normal-light references, where it achieves superior performance on domain-specific datasets alongside better generalization-ability across non-reference datasets.