{"ID":2892213,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.15520","arxiv_id":"2507.15520","title":"SAIGFormer: A Spatially-Adaptive Illumination-Guided Network for Low-Light Image Enhancement","abstract":"Recent Transformer-based low-light enhancement methods have made promising progress in recovering global illumination. However, they still struggle with non-uniform lighting scenarios, such as backlit and shadow, appearing as over-exposure or inadequate brightness restoration. To address this challenge, we present a Spatially-Adaptive Illumination-Guided Transformer (SAIGFormer) framework that enables accurate illumination restoration. Specifically, we propose a dynamic integral image representation to model the spatially-varying illumination, and further construct a novel Spatially-Adaptive Integral Illumination Estimator ($\\text{SAI}^2\\text{E}$). Moreover, we introduce an Illumination-Guided Multi-head Self-Attention (IG-MSA) mechanism, which leverages the illumination to calibrate the lightness-relevant features toward visual-pleased illumination enhancement. Extensive experiments on five standard low-light datasets and a cross-domain benchmark (LOL-Blur) demonstrate that our SAIGFormer significantly outperforms state-of-the-art methods in both quantitative and qualitative metrics. In particular, our method achieves superior performance in non-uniform illumination enhancement while exhibiting strong generalization capabilities across multiple datasets. Code is available at https://github.com/LHTcode/SAIGFormer.git.","short_abstract":"Recent Transformer-based low-light enhancement methods have made promising progress in recovering global illumination. However, they still struggle with non-uniform lighting scenarios, such as backlit and shadow, appearing as over-exposure or inadequate brightness restoration. To address this challenge, we present a Sp...","url_abs":"https://arxiv.org/abs/2507.15520","url_pdf":"https://arxiv.org/pdf/2507.15520v1","authors":"[\"Hanting Li\",\"Fei Zhou\",\"Xin Sun\",\"Yang Hua\",\"Jungong Han\",\"Liang-Jie Zhang\"]","published":"2025-07-21T11:38:56Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false,"code_links":[{"ID":611970,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2892213,"paper_url":"https://arxiv.org/abs/2507.15520","paper_title":"SAIGFormer: A Spatially-Adaptive Illumination-Guided Network for Low-Light Image Enhancement","repo_url":"https://github.com/LHTcode/SAIGFormer.git","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}