Uncertainty-Aware Spatial Color Correlation for Low-Light Image Enhancement

TL;DR

This paper introduces U2CLLIE, a novel low-light image enhancement framework that incorporates uncertainty modeling and spatial-color causal correlation to improve image quality under extremely dark conditions.

Contribution

The paper proposes a new framework combining uncertainty-aware denoising and hierarchical causal correlation modeling for low-light image enhancement, addressing noise and feature uncertainty issues.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Demonstrates robustness and generalization across various scenes.

Effectively suppresses noise and enhances textures in low-light images.

Abstract

Most existing low-light image enhancement approaches primarily focus on architectural innovations, while often overlooking the intrinsic uncertainty within feature representations particularly under extremely dark conditions where degraded gradient and noise dominance severely impair model reliability and causal reasoning. To address these issues, we propose U2CLLIE, a novel framework that integrates uncertainty-aware enhancement and spatial-color causal correlation modeling. From the perspective of entropy-based uncertainty, our framework introduces two key components: (1) An Uncertainty-Aware Dual-domain Denoise (UaD) Module, which leverages Gaussian-Guided Adaptive Frequency Domain Feature Enhancement (G2AF) to suppress frequency-domain noise and optimize entropy-driven representations. This module enhances spatial texture extraction and frequency-domain noise suppression/structure refinement, effectively mitigating gradient vanishing and noise dominance. (2) A hierarchical causality-aware framework, where a Luminance Enhancement Network (LEN) first performs coarse brightness enhancement on dark regions. Then, during the encoder-decoder phase, two asymmetric causal correlation modeling modules Neighborhood Correlation State Space (NeCo) and Adaptive Spatial-Color Calibration (AsC) collaboratively construct hierarchical causal constraints. These modules reconstruct and reinforce neighborhood structure and color consistency in the feature space. Extensive experiments demonstrate that U2CLLIE achieves state-of-the-art performance across multiple benchmark datasets, exhibiting robust performance and strong generalization across various scenes.