GeoFF3D实现大规模无人机地图重建，5分钟处理2000张图像。
GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mapping
- 用坐标锚定模型与空间分块框架结合，直接在地理坐标系中重建
- 在9个航拍区块平均精度提升至F@5=0.877，长序列达0.848
- 适合大范围无人机测绘，尤其轨迹近平行时更稳定
现有前馈式3D重建方法通常处理有限图像，在局部或归一化坐标系中恢复相机位姿与几何结构。扩展至大规模无人机测绘需可扩展的多块处理与可靠聚合机制，而全Sim(3)对齐在近共线轨迹下易失稳。本文提出GeoFF3D，融合坐标锚定模型与空间大规模重建框架（SLRF）。该模型利用地理参考相机平移和可选几何先验，直接在重力对齐的Z-up度量坐标系中预测相机位姿与稠密点云。SLRF将图像划分为空间重叠的块，传播共享视图先验，并分层聚合局部重建，同时兼容不同受限视角模型。在九个航空测绘区块上，GeoFF3D平均重建质量最优，F@5从Pi3X + SLRF的0.829提升至0.877；在长序列UAVScenes上达到0.848，远超Pi3X + SLRF的0.687与最强评估基线的0.451。系统可于约五分钟内重建2000张图像，展现高效稳健的大规模无人机重建能力。代码已开源。
原文摘要 · Abstract (English)
Existing feed-forward 3D reconstruction methods typically process a bounded number of images and recover cameras and geometry in local or internally normalized frames. Extending them to large-scale UAV mapping requires scalable multi-chunk processing and reliable aggregation, while full Sim(3) alignment can become unstable for near collinear trajectories. We present GeoFF3D, which combines a coordinate-anchored model with a spatial large-scale reconstruction framework (SLRF). The model uses georeferenced camera translations and optional geometric priors to predict camera poses and dense point maps directly in a gravity-aligned Z-up metric frame. SLRF partitions images into spatially overlapping chunks, propagates shared-view priors, and aggregates local reconstructions hierarchically, while remaining applicable to different bounded-view models. Across nine aerial mapping blocks, GeoFF3D achieves the best average reconstruction quality, improving F@5 from 0.829 for Pi3X + SLRF to 0.877. On long UAVScenes sequences, it reaches 0.848, compared with 0.687 for Pi3X + SLRF and 0.451 for the strongest evaluated SLAM/streaming baseline. GeoFF3D reconstructs 2,000 images in approximately five minutes, demonstrating scalable and robust large-scale UAV reconstruction.The code is available at https://github.com/yanxian-ll/GeoFF3D.
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。