GeoFF3D：用于大规模无人机测绘的坐标锚定前馈重建方法
GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mapping
查看机构详情
- Central South University（中南大学）
- Hunan Engineering Research Center of 3D Real Scene Construction and Application Technology（湖南省3D真实场景构建与应用技术工程研究中心）
- National University of Defense Technology（国防科技大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
GeoFF3D结合坐标锚定模型与SLRF框架，解决大规模无人机测绘问题，在9个航空块及UAVScenes序列上的重建质量优于基线，可高效处理2000张图像。
中文摘要 AI 辅助
现有前馈三维重建方法通常处理有限数量的图像，并在局部或内部归一化坐标系中恢复相机与几何结构。将其扩展至大规模无人机测绘需具备可扩展的多块处理与可靠聚合能力，而对于近共线轨迹，全Sim(3)对齐可能变得不稳定。本文提出GeoFF3D，它结合了坐标锚定模型与空间大规模重建框架（SLRF）。该模型使用地理配准的相机平移及可选几何先验，直接在重力对齐的Z向上度量坐标系中预测相机位姿与稠密点云图。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结果，同时适用于不同的有限视图模型。在9个航空测绘块上，GeoFF3D实现了最佳平均重建质量，将F@5指标从Pi3X+SLRF的0.829提升至0.877；在长UAVScenes序列上，其得分为0.848，而Pi3X+SLRF为0.687，评估中最强的SLAM/流式基线仅为0.451。GeoFF3D可在约5分钟内重建2000张图像，展现出可扩展且鲁棒的大规模无人机测绘能力，代码可在指定链接获取。
英文摘要
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.
