首个多角度无人机作物3D重建基准，揭示现有方法在农业应用中的局限性
UAV3DCrop: Benchmarking 3D Reconstruction in Repeated Multi-Angle UAV Crop Surveys
- 构建91个农田场景的重复多视角无人机影像数据集，含8.8万张高分辨率图像
- 不同模型在外观、深度和冠层高度上表现差异大，无一全能；仅一个模型恢复可用尺度
- 揭示了采集顺序和特征点数量对重建质量的影响，提示实际应用需考虑时间序列因素
精准的3D作物监测是数据驱动精准农业的基础，可实现田间植物结构、生长动态与管理响应的大规模分析。现代3D重建方法在通用基准上表现良好，但渲染外观未必转化为农学上有用的度量几何。本文提出UAV3DCrop，一个公开的重复多角度无人机作物调查基准。包含88,830张分辨率为5280×3956像素的RGB图像，地面采样距离为3.6-5.8毫米，覆盖玉米、大豆、小麦和燕麦共91个场景。Track A评估七种场景优化方法（NeRF与3DGS变体）在未见视图、摄影测量参考深度及冠层高度恢复上的表现；Track B测试四个预训练前馈模型在零样本相机位姿与几何估计上的能力。场景优化方法在三类任务中排名不同：Splatfacto-big在外观上领先，Scaffold-GS在深度上最优，且与Splatfacto在冠层高度上统计持平。前馈模型中，MapAnything在八项指标中有七项领先，其余模型在不同作物间表现波动大，且绝对尺度恢复严重失败，虽可通过对齐掩盖问题。重复采集结果揭示了输出类型与模型相关的敏感性，与采集序列位置及特征点多重性有关。当前3D重建方法尚未适用于农业场景：无一方法在外观、几何和冠层高度上全部领先，且四款前馈模型中仅一款能恢复可用度量尺度。数据集已公开于https://link-dev.github.io/UAV3DCrop/
原文摘要 · Abstract (English)
Accurate 3D crop monitoring underpins data-driven precision agriculture by enabling field-scale analysis of plant structure, growth dynamics, and management response. Modern 3D reconstruction methods perform strongly on generic benchmarks, but rendered appearance may not translate into metrically and agronomically useful geometry in crop fields. We introduce UAV3DCrop, a public benchmark of repeated multi-angle unmanned aerial vehicle (UAV) crop surveys. It contains 88,830 RGB images at $5280 \times 3956$ pixels, with a ground sampling distance of 3.6-5.8 mm, from 91 scenes spanning corn, soybean, wheat, and oat. Track A evaluates seven scene-optimized methods -- Neural Radiance Field (NeRF) and 3D Gaussian Splatting (3DGS) variants -- on held-out views, photogrammetry-referenced depth, and canopy-height recovery. Track B tests four pretrained feed-forward models on zero-shot camera-pose and geometry estimation. The scene-optimized methods rank differently across the three targets: Splatfacto-big leads appearance, whereas Scaffold-GS leads depth and is statistically tied with Splatfacto for canopy height. Among feed-forward models, MapAnything leads on seven of the eight metrics, while the remaining models vary more across crops and fail severely on absolute scale in a way that alignment conceals. Repeated acquisitions reveal further sensitivities that differ by output type and by model, associated with position within the acquisition sequence and with tie-point multiplicity. Current 3D reconstruction methods are therefore not yet interchangeable for agronomic use: no single method wins on appearance, geometry, and canopy height at once, and only one of four feed-forward models recovers usable metric scale. The dataset is publicly available at https://link-dev.github.io/UAV3DCrop/
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。