UAVFF3D: A Geometry-Aware Benchmark for Feed-Forward UAV 3D Reconstruction
It provides a dedicated benchmark and evaluation protocol for UAV 3D reconstruction, addressing a gap in existing methods that fail under UAV-specific geometric ambiguities.
The paper introduces UAVFF3D, a benchmark with over 540K images for feed-forward UAV 3D reconstruction, and shows that domain adaptation reduces Ray Error by up to 84.2%, Pose ATE by up to 76.0%, and Chamfer Distance by up to 41.1% on four representative models.
Feed-forward 3D reconstruction has recently demonstrated strong generalization across diverse scenes, yet its performance in UAV imagery remains underexplored due to distinctive acquisition geometries, large viewpoint variations, and ambiguity between horizontal field of view and flight height. We present UAVFF3D, a geometry-aware benchmark for feed-forward UAV 3D reconstruction, comprising over 170K real UAV images and more than 370K high-quality synthetic images. The benchmark also includes a challenging diagnostic test subset designed to analyze model behavior under UAV-specific geometric ambiguities.Building on UAVFF3D, we propose an evaluation protocol that jointly assesses camera-geometry estimation and reconstruction accuracy, addressing limitations of existing evaluations that rely on separate alignments. Experiments on four representative feed-forward reconstruction models show that UAV-domain adaptation substantially improves performance, reducing Ray Error by up to 84.2%, Pose ATE by up to 76.0%, and Chamfer Distance by up to 41.1%. Further analysis reveals that domain adaptation mitigates rotation-estimation degradation in oblique-view scenes and improves robustness under horizontal-field-of-view/height ambiguity. Incorporating camera priors further enhances reconstruction performance under UAV-specific acquisition geometries.