UAVLight: A Benchmark for Illumination-Robust 3D Reconstruction in Unmanned Aerial Vehicle (UAV) Scenes
This addresses the challenge of lighting variations in outdoor UAV-based reconstruction, providing a controlled benchmark for developing illumination-robust methods, though it is incremental as it focuses on dataset creation rather than a new algorithmic solution.
The paper tackles the problem of illumination inconsistency in multi-view 3D reconstruction for UAV scenes by introducing UAVLight, a benchmark dataset that captures scenes at multiple times of day under consistent geometry and viewpoints, enabling standardized evaluation of methods for robust and relightable reconstruction.
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.