超越光照：一种条件互信息引导的低光照图像增强网络
Beyond Illumination: A Conditional Mutual Information-Guided Network for Low-Light Image Enhancement
AI总结：
针对现有低光照图像增强方法忽略亮度与色度分量相互作用的局限，提出CMIG-Net网络，通过CMIC和D2IR模块提升性能，在PSNR上较CIDNet最高提升0.619 dB，在Sony-Total-Dark数据集上提升0.382 dB。
AI中文摘要：
低光照图像增强（LLIE）旨在从光照不足条件下采集的图像中恢复结构保真度、自然色彩还原度和合适的曝光度。近期最先进的方法，如CIDNet，采用双分支架构，包含色度（HV）分支和亮度（I）分支，以在HVI色彩空间内分别建模解耦的色度和亮度信息。然而，这些方法忽略了亮度与色度分量之间的相互作用，这固有地限制了它们的表征能力，并导致增强性能欠佳。为解决这一局限，我们提出了条件互信息引导网络（CMIG-Net），该网络利用条件互信息作为原则性度量，以量化评估在可用亮度信息条件下色度特征的贡献。具体而言，我们设计了条件互信息校准（CMIC）模块，该模块生成条件信息图，从而能够根据局部光照统计数据对色度表示进行区域自适应重新校准。此外，我们引入了动态双分支信息恢复（D2IR）模块，该模块在条件先验和瞬时恢复状态的引导下，自适应地调控亮度与色度分支之间的双向信息流。在配对LLIE基准上进行的大量实验表明，CMIG-Net始终优于CIDNet，在峰值信噪比（PSNR）上实现了高达0.619 dB的增益，在具有挑战性的Sony-Total-Dark数据集上更是实现了0.382 dB的提升。
英文摘要：
Low-light image enhancement (LLIE) seeks to restore structural fidelity, natural color rendition, and proper exposure from images captured under inadequate lighting conditions. Recent state-of-the-art approaches, such as CIDNet, adopt a dual-branch architecture comprising a chrominance (HV) branch and an intensity (I) branch to separately model decoupled chromatic and luminance information within the HVI color space. However, these methods overlook the mutual interaction between intensity and chrominance components, which inherently limits their representational capacity and leads to suboptimal enhancement performance. To address this limitation, we propose the Conditional Mutual Information-Guided Network (CMIG-Net), which leverages conditional mutual information as a principled metric to quantitatively assess the contribution of chrominance features conditioned on the available intensity information. In particular, we design a Conditional Mutual Information Calibration (CMIC) module that generates a conditional information map, enabling region-adaptive recalibration of chrominance representations according to local illumination statistics. Furthermore, we introduce a Dynamic Dual-branch Information Restoration (D2IR) module, which adaptively governs bidirectional information flow between the intensity and chrominance branches, guided by both the conditional prior and the instantaneous restoration state. Extensive experiments on paired LLIE benchmarks demonstrate that CMIG-Net consistently outperforms CIDNet, achieving up to a 0.619 dB gain in PSNR, with a 0.382 dB improvement specifically on the challenging Sony-Total-Dark dataset.
