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.
Abstract (translated)
大多数现有的低光图像增强方法主要集中在架构创新上，而常常忽略了在极端黑暗条件下特征表示内在不确定性的问题。在这种情况下，退化的梯度和噪声主导效应会严重损害模型的可靠性和因果推理能力。为解决这些问题，我们提出了一种新的框架U2CLLIE（Uncertainty-aware Enhancement and Spatial-Color Causal Correlation Modeling），该框架集成了基于不确定性的增强功能以及空间色彩因果关系建模。 从熵基不确定性视角出发，我们的框架引入了两个关键组件： 1. **不确定性感知双域去噪模块 (Uncertainty-Aware Dual-domain Denoise, UaD)**：此模块利用高斯引导自适应频域特征增强（Gaussian-Guided Adaptive Frequency Domain Feature Enhancement, G2AF）来抑制频域噪声，并优化熵驱动表示。该模块增强了空间纹理提取以及频率域中的噪声抑制和结构细化能力，有效地缓解了梯度消失及噪声主导问题。 2. **层次因果框架**：在这一部分中，亮度增强网络（Luminance Enhancement Network, LEN）首先对暗区域进行粗略的亮度提升处理。然后，在编码器-解码器阶段，两个非对称因果关系建模模块“邻域相关状态空间”（Neighborhood Correlation State Space, NeCo）和“自适应空间色彩校准”（Adaptive Spatial-Color Calibration, AsC），共同构建了分层的因果约束。这些模块在特征空间中重建并增强了相邻结构和颜色一致性。 广泛的实验表明，U2CLLIE框架在多个基准数据集上取得了最先进的性能，在各种场景下均表现出强大的稳健性和泛化能力。
URL
https://arxiv.org/abs/2508.04176
