AdaAnchor4D: Anchor-Conditioned Spatiotemporal Feature Aggregation for Monocular UAV 4D Reconstruction

2026-07-30

AI Summary

This work addresses the challenges of motion blur and ghosting artifacts in dynamic scene reconstruction from monocular UAV videos captured in complex urban environments, where spatiotemporal heterogeneity hinders accurate modeling. To this end, we propose an adaptive anchor deformation framework that introduces Anchor-Conditioned Feature Aggregation (ACFA) to effectively integrate contextual information. The method decouples local geometric deformation via Decoupled Local Geometry Deformation (DLGD), separating anchor states from Gaussian deformations, and further incorporates Density-Adaptive Coordinate Warping (DACW) to reparameterize query positions, enabling precise modeling of heterogeneous dynamic regions. Evaluated on UAV-Arc4D, VisDrone, and UAVDT datasets, our approach significantly outperforms existing dynamic Gaussian reconstruction methods, achieving superior fidelity in dynamic details while maintaining real-time rendering performance.

Abstract

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.

Problem

• monocular UAV
• 4D reconstruction
• spatiotemporal heterogeneity
• dynamic scene
• ghosting artifacts

Innovation

• Anchor-Conditioned Feature Aggregation
• Decoupled Local Geometry Deformation
• Density-Adaptive Coordinate Warping
• Dynamic Scene Reconstruction
• Monocular UAV 4D