用伪参考图增强夜间航拍图像，提升真实感与曝光平衡。
AeroLLE: Constrained Pseudo-Supervision for Nighttime Aerial Image Enhancement with the AeroNight-1.5K Benchmark
- 分两阶段：先恢复可见性，再做空间自适应曝光-色彩校准。
- 在1500张真实夜间航拍图上验证，显著改善光照均匀性。
- 适合无真实参考图时的夜间航拍增强任务。
夜间航拍图像增强面临空间非均匀曝光、混合光照和结构信息弱等问题，且移动平台难以获取真实正常光照参考图。生成的正常光照图像可提供外观指导，但可能改变几何或纹理。我们提出 AeroNight，包含1,500张真实夜间航拍RGB图像：1,300张配有手动筛选的伪参考图，200张用于无配对评估。提出AeroLLE框架，分两阶段进行：第一阶段使用HVI Base Enhancer恢复可见性；第二阶段进行空间自适应曝光-色彩校准（SAECC），预测受约束的低分辨率RGB增益与偏置场，限制二次校正的幅度与空间变化。在互补伪配对与无配对协议下实验表明，该方法更接近筛选后的外观目标，且在多类夜间航拍场景中实现更均衡的曝光与色彩校正。结果支持在缺乏真实参考图时，采用受限、分阶段校准作为学习生成外观引导的有效策略。
原文摘要 · Abstract (English)
Nighttime aerial image enhancement is challenged by spatially nonuniform exposure, mixed illumination, and weak structural evidence, while registered normal-light targets are difficult to capture from moving platforms. Generated normal-light images provide practical appearance guidance but may alter geometry or texture. We introduce \aeronight{}, comprising 1,500 real nighttime aerial RGB images: 1,300 inputs are associated with manually screened pseudo-references, and 200 inputs support unpaired evaluation. We propose AeroLLE, a two-stage framework that first recovers visibility with an HVI Base Enhancer and then performs Spatially Adaptive Exposure--Color Calibration (SAECC). After the Base Enhancer is selected and frozen, SAECC predicts bounded, low-resolution RGB gain and bias fields, restricting the magnitude and spatial variation of the second-stage correction. Experiments under complementary pseudo-paired and unpaired protocols demonstrate improved agreement with screened appearance targets, together with more balanced exposure and color correction across diverse nighttime aerial scenes. These results support constrained, stage-specific calibration as a practical strategy for learning from generated appearance guidance when registered aerial references are unavailable.
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。