AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World
For researchers and practitioners in UAV-based depth estimation, this work provides a much-needed benchmark and adaptation method to overcome the domain gap from ground-level to aerial viewpoints.
This paper introduces AerialMetric, a benchmark dataset of 52K real and 16K synthetic aerial image-depth pairs for monocular metric depth estimation in UAV imagery. Fine-tuning a representative model on this dataset achieves state-of-the-art performance across diverse aerial scenes.
This paper addresses the problem of monocular metric depth estimation in aerial UAV imagery. Although recent data-driven methods have achieved remarkable progress in ground-level scenarios, models trained primarily on street-view and indoor datasets exhibit significant domain gaps when applied to aerial viewpoints. To tackle these challenges, we introduce AerialMetric, a benchmark dataset designed to evaluate and facilitate the adaptation of monocular metric depth estimation under UAV aerial viewpoints. The dataset consists of four complementary subsets collected from different sources, jointly covering real-world photogrammetry data, controlled aerial acquisition settings, photorealistic synthetic scenes, and in-the-wild Internet imagery. Totally, AerialMetric provides 52K real-world and 16K synthetic image-depth pairs with reliable metric ground truth. Based on this dataset, we conduct systematic evaluations of existing state-of-the-art models under aerial settings and investigate the impact of viewpoint, altitude, and camera parameters on metric depth prediction. In addition, by fine-tuning representative metric depth model on our dataset, we establish a comprehensive aerial benchmark and achieve state-of-the-art performance across diverse aerial imagery. Our dataset, code, and model weight are publicly available at https://kuieless.github.io/AerialMetric-ECCV2026-page/.