UAVLight: A Benchmark for Illumination-Robust 3D Reconstruction in Unmanned Aerial Vehicle (UAV) Scenes

2025-11-26

AI Summary

To address geometric drift, color distortion, and shadow artifacts induced by illumination inconsistency in UAV-based multi-view 3D reconstruction, this paper introduces the first illumination-robustness benchmark dataset for UAVs. It acquires high-fidelity image sequences and precise camera calibration parameters under natural illumination variations across multiple time slots, via repeatable georeferenced fixed-path flights—explicitly decoupling illumination changes from geometric and viewpoint variations. Methodologically, it integrates multi-view stereo (MVS), structure-from-motion (SfM), and neural rendering, and proposes a standardized cross-illumination reconstruction evaluation protocol. This benchmark enables quantitative, real-world outdoor assessment of algorithmic robustness to illumination variation. It establishes a reliable foundation for evaluating illumination-consistent reconstruction and relightable 3D modeling, thereby advancing the practical deployment of 3D reconstruction in open, uncontrolled environments.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

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.

Problem

• Addresses illumination inconsistency in UAV multi-view 3D reconstruction
• Solves geometry drift and shadow artifacts from lighting variations
• Provides benchmark for robust reconstruction under natural illumination changes

Innovation

• Benchmark with geo-referenced flight paths
• Multiple fixed times of day capture
• Standardized evaluation under consistent geometry