AeroGS：面向无位姿动态无人机场景重建的尺度感知高斯泼溅
AeroGS: Scale-Aware Gaussian Splatting for Pose-Free Dynamic UAV Scene Reconstruction
把相机位姿与动态场景联合优化拆成自运动/物体运动、静态几何/时序形变、远近尺度三层解耦，并用尺度感知的时空锚点承载，可直接迁移到无位姿单目视频的动态高斯泼溅重建与轨迹估计。
原文依据 scale-aware spatio-temporal anchors (S2A-Anchors), which enable a unified optimization via three key decoupling mechanisms
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论单目无人机视频为三维重建带来了根本性挑战：动态场景建模需要准确的相机位姿，而从长距离无人机轨迹中恢复位姿往往在纹理稀疏区域以及存在运动物体的情形下失败。现有方法通常只处理无位姿的静态重建，或处理位姿已知的动态重建，但由于运动耦合与剧烈的尺度变化，从随意的航拍视频中同时求解二者仍然困难。我们提出 AeroGS，一个尺度感知的高斯泼溅框架，可从无位姿单目视频中联合恢复相机轨迹并重建动态场景。本方法的核心是尺度感知时空锚点（S2A-Anchors），它通过三种关键解耦机制实现统一优化：(i) 将自运动与物体运动分离，(ii) 将静态几何与时序形变隔离，(iii) 适应远景地形与近处物体之间的尺度变化。该设计有效稳定了大运动与尺度失衡条件下的优化。在无人机与自动驾驶基准上的大量实验表明，AeroGS 取得了最优的渲染质量（PSNR/LPIPS）、精确的轨迹恢复（ATE/RPE）以及忠实的运动重建，持续超越近期的无位姿基线方法。
英文原文摘要 1342 字符
Monocular UAV videos pose a fundamental challenge for 3D reconstruction: dynamic scene modeling requires accurate camera poses, yet recovering poses from long UAV trajectories often fails in texture-sparse regions and in the presence of moving objects. Existing approaches typically handle either pose-free static reconstruction or dynamic reconstruction with known poses, but jointly solving both from casual aerial footage remains difficult due to motion coupling and severe scale variation. We introduce AeroGS, a scale-aware Gaussian splatting framework that jointly recovers camera trajectories and reconstructs dynamic scenes from pose-free monocular videos. Central to our method are scale-aware spatio-temporal anchors (S2A-Anchors), which enable a unified optimization via three key decoupling mechanisms: (i) separating ego-motion from object motion, (ii) isolating static geometry from temporal deformation, and (iii) adapting to scale variation between distant terrain and nearby objects. This design effectively stabilizes optimization under large motion and scale imbalance. Extensive experiments on UAV and driving benchmarks show that AeroGS achieves state-of-the-art rendering quality (PSNR/LPIPS), precise trajectory recovery (ATE/RPE), and faithful motion reconstruction, consistently surpassing recent pose-free baselines.