Abstract
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: this https URL
Abstract (translated)
在傅里叶域中，亮度信息主要编码在振幅谱中，而空间结构则捕获于相位组件中。传统的傅里叶频率信息拟合采用像素级损失函数，这种做法往往会过度关注局部信息，并可能导致全局信息的丢失。本文介绍了 LLFDisc，这是一个 U 形深度增强网络，集成了专为频域感知增强设计的交叉注意力和门控机制。我们提出了一种新颖的基于分布感知的损失方法，该方法直接拟合傅里叶域的信息并使用闭式 KL 散度目标函数最小化它们之间的差异。这使得模型能够比传统的基于 MSE 的损失更稳健地对齐傅里叶域信息。此外，我们在 VGG 基础上改进了感知损失，并通过在提取的深度特征中嵌入 KL 散度来增强结构保真度。广泛的跨多个基准测试的实验表明，LLFDisc 在定性和定量评估中均达到了最先进的性能。我们的代码将在以下链接发布：this https URL
URL
https://arxiv.org/abs/2509.13083
