{"ID":2875872,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.01373","arxiv_id":"2509.01373","title":"Unsupervised Ultra-High-Resolution UAV Low-Light Image Enhancement: A Benchmark, Metric and Framework","abstract":"Low light conditions significantly degrade Unmanned Aerial Vehicles (UAVs) performance in critical applications. Existing Low-light Image Enhancement (LIE) methods struggle with the unique challenges of aerial imagery, including Ultra-High Resolution (UHR), lack of paired data, severe non-uniform illumination, and deployment constraints. To address these issues, we propose three key contributions. First, we present U3D, the first unsupervised UHR UAV dataset for LIE, with a unified evaluation toolkit. Second, we introduce the Edge Efficiency Index (EEI), a novel metric balancing perceptual quality with key deployment factors: speed, resolution, model complexity, and memory footprint. Third, we develop U3LIE, an efficient framework with two training-only designs-Adaptive Pre-enhancement Augmentation (APA) for input normalization and a Luminance Interval Loss (L_int) for exposure control. U3LIE achieves SOTA results, processing 4K images at 23.8 FPS on a single GPU, making it ideal for real-time on-board deployment. In summary, these contributions provide a holistic solution (dataset, metric, and method) for advancing robust 24/7 UAV vision. The code and datasets are available at https://github.com/lwCVer/U3D_Toolkit.","short_abstract":"Low light conditions significantly degrade Unmanned Aerial Vehicles (UAVs) performance in critical applications. Existing Low-light Image Enhancement (LIE) methods struggle with the unique challenges of aerial imagery, including Ultra-High Resolution (UHR), lack of paired data, severe non-uniform illumination, and depl...","url_abs":"https://arxiv.org/abs/2509.01373","url_pdf":"https://arxiv.org/pdf/2509.01373v1","authors":"[\"Wei Lu\",\"Lingyu Zhu\",\"Si-Bao Chen\"]","published":"2025-09-01T11:20:07Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":610252,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2875872,"paper_url":"https://arxiv.org/abs/2509.01373","paper_title":"Unsupervised Ultra-High-Resolution UAV Low-Light Image Enhancement: A Benchmark, Metric and Framework","repo_url":"https://github.com/lwCVer/U3D_Toolkit","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}