{"ID":2870443,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.13083","arxiv_id":"2509.13083","title":"Using KL-Divergence to Focus Frequency Information in Low-Light Image Enhancement","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: https://github.com/YanXY000/LLFDisc","short_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...","url_abs":"https://arxiv.org/abs/2509.13083","url_pdf":"https://arxiv.org/pdf/2509.13083v2","authors":"[\"Yan Xingyang\",\"Huang Xiaohong\",\"Zhang Zhao\",\"You Tian\",\"Xu Ziheng\"]","published":"2025-09-16T13:40:06Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":609764,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2870443,"paper_url":"https://arxiv.org/abs/2509.13083","paper_title":"Using KL-Divergence to Focus Frequency Information in Low-Light Image Enhancement","repo_url":"https://github.com/YanXY000/LLFDisc","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}