构建多光照强度数据集，评估低光增强算法在不同亮度下的表现。
Evaluating Low-Light Image Enhancement Across Multiple Intensity Levels
- 提出MILL数据集，覆盖多种可控光照条件下的图像。
- 发现现有算法在不同亮度下性能差异显著，部分提升达10 dB PSNR。
- 改进算法增强跨光照场景的鲁棒性，适合手机与相机应用。
低光环境成像因场景辐射度降低，导致传感器噪声增加和色彩饱和度下降，面临挑战。当前基于学习的低光增强方法通常依赖单一低光条件与明亮参考图像的配对数据，缺乏辐射度多样性，难以全面评估算法在不同光照下的表现。本文提出多光照低光（MILL）数据集，在固定相机设置和精确照度测量条件下，采集了多种光照强度的图像，支持对增强算法在多变光照下的系统评估。我们基准测试了多个前沿方法，揭示其在不同亮度层级上存在显著性能波动。利用数据集独特的多光照结构，提出改进方案，提升了算法在多样化照明场景中的鲁棒性。改进后的方法在全高清图像上，对数码单反相机实现最高10 dB的PSNR提升，对智能手机实现2 dB提升。
原文摘要 · Abstract (English)
Imaging in low-light environments is challenging due to reduced scene radiance, which leads to elevated sensor noise and reduced color saturation. Most learning-based low-light enhancement methods rely on paired training data captured under a single low-light condition and a well-lit reference. The lack of radiance diversity limits our understanding of how enhancement techniques perform across varying illumination intensities. We introduce the Multi-Illumination Low-Light (MILL) dataset, containing images captured at diverse light intensities under controlled conditions with fixed camera settings and precise illuminance measurements. MILL enables comprehensive evaluation of enhancement algorithms across variable lighting conditions. We benchmark several state-of-the-art methods and reveal significant performance variations across intensity levels. Leveraging the unique multi-illumination structure of our dataset, we propose improvements that enhance robustness across diverse illumination scenarios. Our modifications achieve up to 10 dB PSNR improvement for DSLR and 2 dB for the smartphone on Full HD images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。