构建无人机场景光照鲁棒重建基准，解决户外光照变化导致的三维重建失真问题。
UAVLight: A Benchmark for Illumination-Robust 3D Reconstruction in Unmanned Aerial Vehicle (UAV) Scenes
- 在相同飞行路径上多时段采集，保持几何与视角一致，仅改变光照条件。
- 支持在真实自然光照下评估重建方法，避免阴影和颜色漂移问题。
- 适合研究光照鲁棒性、无人机三维重建与神经渲染的开发者使用。
光照不一致是多视角三维重建的核心挑战。阳光方向、云层遮挡和阴影变化破坏了经典多视图立体（MVS）与运动恢复结构（SfM）流程，以及近期神经渲染方法所依赖的恒定光照假设，导致几何漂移、色彩不一致和阴影残留。该问题在无人机（UAV）重建中尤为严重，因长时间飞行与户外环境使光照变化不可避免。现有数据集或仅覆盖短时间窗口，缺乏有效光照多样性；或跨越数月季节，几何与语义变化干扰光照鲁棒性的独立研究。本文提出UAVLight，一个受控但真实的光照鲁棒三维重建基准。每个场景沿可重复、地理标记的飞行路径，在多个固定时段采集，实现一致几何、标定与视角下的自然光照变化。通过标准化的评估协议，UAVLight为开发和评测在真实室外环境中具有一致性、忠实性和可重光照能力的重建方法提供了可靠基础。
原文摘要 · Abstract (English)
Illumination inconsistency is a fundamental challenge in multi-view 3D reconstruction. Variations in sunlight direction, cloud cover, and shadows break the constant-lighting assumption underlying both classical multi-view stereo (MVS) and structure from motion (SfM) pipelines and recent neural rendering methods, leading to geometry drift, color inconsistency, and shadow imprinting. This issue is especially critical in UAV-based reconstruction, where long flight durations and outdoor environments make lighting changes unavoidable. However, existing datasets either restrict capture to short time windows, thus lacking meaningful illumination diversity, or span months and seasons, where geometric and semantic changes confound the isolated study of lighting robustness. We introduce UAVLight, a controlled-yet-real benchmark for illumination-robust 3D reconstruction. Each scene is captured along repeatable, geo-referenced flight paths at multiple fixed times of day, producing natural lighting variation under consistent geometry, calibration, and viewpoints. With standardized evaluation protocols across lighting conditions, UAVLight provides a reliable foundation for developing and benchmarking reconstruction methods that are consistent, faithful, and relightable in real outdoor environments.
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。