用KL散度聚焦频域信息，提升低光图像增强效果
Using KL-Divergence to Focus Frequency Information in Low-Light Image Enhancement
- 设计频域感知网络，用KL散度直接拟合傅里叶谱分布
- 相比传统MSE损失，频域对齐更稳健，结构保留更好
- 适合追求细节还原的低光图像处理研究者
在傅里叶域中，亮度信息主要编码于幅度谱，空间结构则由相位成分捕获。传统傅里叶频域拟合采用像素级损失函数，过度关注局部信息，易导致全局信息丢失。本文提出一种U型深度增强网络LLFDisc，融合交叉注意力与门控机制，实现频域感知增强。设计了一种新的分布感知损失，直接拟合傅里叶域信息，并利用闭式KL散度目标最小化其差异，使模型在频域信息对齐上比传统MSE损失更具鲁棒性。此外，基于VGG的感知损失通过嵌入提取特征上的KL散度，提升了结构保真度。多基准测试表明，LLFDisc在定性和定量评估中均达到当前最优性能。代码将公开于：https://github.com/YanXY000/LLFDisc
原文摘要 · Abstract (English)
In the Fourier domain, luminance information is primarily encoded in the amplitude spectrum, while spatial structures are captured in the phase components. The traditional Fourier Frequency information fitting employs pixel-wise loss functions, which tend to focus excessively on local information and may lead to global information loss. In this paper, we present LLFDisc, a U-shaped deep enhancement network that integrates cross-attention and gating mechanisms tailored for frequency-aware enhancement. We propose a novel distribution-aware loss that directly fits the Fourier-domain information and minimizes their divergence using a closed-form KL-Divergence objective. This enables the model to align Fourier-domain information more robustly than with conventional MSE-based losses. Furthermore, we enhance the perceptual loss based on VGG by embedding KL-Divergence on extracted deep features, enabling better structural fidelity. Extensive experiments across multiple benchmarks demonstrate that LLFDisc achieves state-of-the-art performance in both qualitative and quantitative evaluations. Our code will be released at: https://github.com/YanXY000/LLFDisc
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。