AirAlign：面向无人机最后一米导航的几何感知相对位姿对齐
AirAlign: Geometry-Aware Relative Pose Alignment for UAV Last-Meter Navigation
- Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对无人机最后一米导航中视角与外观变化导致的位姿对齐难题，提出仅用RGB图像对的AirAlign框架，结合预训练几何模型与场景拆分训练，经PairUAV挑战赛实验验证其有效性与鲁棒性。
AI中文摘要：
现代低空环境中的无人机（UAV）导航在最终进近阶段需要更精准的位姿对齐，以完成目标信息获取或操作，这使得“最后一米”导航愈发重要。但严重的视角与外观变化让该任务极具挑战性。为解决此问题，我们提出AirAlign，一种仅用RGB图像对实现无人机相对位姿对齐的框架。AirAlign采用预训练视觉几何重建模型作为骨干网络，从源-目标图像对中提取几何感知特征。此外，为更好利用有限的训练数据，我们将训练集拆分为多个场景不重叠的折，用于未见场景的交叉验证与模型选择。推理阶段，将所选模型的预测结果取平均，形成整个框架的集成输出。在ACMMM 2026无人机多媒体研讨会上的PairUAV挑战赛上的实验，证明了我们方法的有效性与鲁棒性，全面的消融研究则验证了各组件的贡献。
英文摘要：
Unmanned aerial vehicle (UAV) navigation in modern low-altitude environments requires more accurate pose alignment in the final approach stage for target information acquisition or manipulation, making "last-meter" navigation increasingly important. However, severe viewpoint and appearance variations make this task challenging. To tackle this problem, we propose AirAlign, a framework for RGB-only image-pair relative pose alignment for UAVs. AirAlign uses a pretrained visual geometry reconstruction model as the backbone to extract geometry-aware features from source-target image pairs. In addition, to better utilize the limited training data, we split the training set into multiple scene-disjoint folds for unseen cross-validation and model selection. During inference, the predictions of the selected models are averaged to form the ensemble output of the overall framework. Experiments on the PairUAV challenge at the ACMMM 2026 Workshop on UAVs in Multimedia demonstrate the effectiveness and robustness of our method, while comprehensive ablation studies validate the contribution of each component.
