AI 中文总结
该研究针对单目无人机4D重建中动态高斯方法的缺陷，提出AdaAnchor4D框架，通过ACFA、DLGD和DACW技术提升渲染质量，在多个无人机数据集上优于现有方法且保持实时性。
AI 中文摘要
单目无人机视频为复杂城市场景的动态重建提供了宝贵观测数据，但这类场景存在显著的时空异质性：不同区域遵循不同的时间活动模式，部分动态区域的运动状态还会随时间演变。尽管基于分解共享时空特征场的动态高斯方法已在以对象为中心或相对紧凑的场景中实现了高效准确的重建，但其普遍采用的固定平面式特征组合机制并不适配无人机场景的异构局部动态，常导致重影伪影和动态细节模糊。为应对这一挑战，我们提出AdaAnchor4D，一种面向单目无人机动态场景重建的自适应锚变形框架。其核心是锚条件特征聚合（ACFA），该方法利用锚特定聚合嵌入和时间信息自适应聚合共享时空特征，使不同局部单元获得适配其局部和时间状态的动态表示；解耦局部几何变形（DLGD）将锚状态变形与局部高斯几何变形分离；密度自适应坐标扭曲（DACW）则根据轴向锚分布对特征查询坐标进行重参数化，缓解非均匀几何采样与均匀网格参数化之间的不匹配。在UAV-Arc4D、VisDrone和UAVDT数据集上的实验表明，AdaAnchor4D在保持实时渲染性能的同时，比代表性动态高斯方法实现了更高的渲染质量，代码将公开提供。
英文摘要
Monocular UAV videos provide valuable observations for dynamic reconstruction of complex urban scenes. However, such scenes exhibit pronounced spatiotemporal heterogeneity: different regions follow distinct temporal activity patterns, while the motion states of some dynamic regions may further evolve over time. Although dynamic Gaussian methods based on decomposed shared spatiotemporal feature fields have achieved efficient and accurate reconstruction in object-centric or relatively compact scenes, their commonly adopted fixed plane-wise feature combination mechanisms are less suited to the heterogeneous local dynamics of UAV scenes, often leading to ghosting artifacts and blurred dynamic details. To address this challenge, we propose AdaAnchor4D, an adaptive anchor deformation framework for monocular UAV dynamic scene reconstruction. At its core, Anchor-Conditioned Feature Aggregation (ACFA) adaptively aggregates shared spatiotemporal features using anchor-specific aggregation embeddings and temporal information, allowing different local units to obtain dynamic representations tailored to their local and temporal states. Decoupled Local Geometry Deformation (DLGD) separates anchor-state deformation from local Gaussian geometry deformation, while Density-Adaptive Coordinate Warping (DACW) reparameterizes feature-query coordinates according to the axis-wise anchor distributions, alleviating the mismatch between non-uniform geometric sampling and uniform grid parameterization. Experiments on UAV-Arc4D, VisDrone, and UAVDT show that AdaAnchor4D achieves higher rendering quality than representative dynamic Gaussian methods while maintaining real-time rendering performance. The code will be made publicly available.
Comments9 pages, 4 figures
