Unsupervised Ultra-High-Resolution UAV Low-Light Image Enhancement: A Benchmark, Metric and Framework
This work provides a holistic solution for improving UAV vision in low-light conditions, which is critical for applications like surveillance and monitoring, though it is incremental in combining existing ideas into a domain-specific framework.
The paper tackles the problem of enhancing low-light images from unmanned aerial vehicles (UAVs) by addressing challenges like ultra-high resolution and lack of paired data, resulting in a framework that processes 4K images at 23.8 FPS and achieves state-of-the-art performance.
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.