DAPM: UAV Monocular Depth Estimation from Any Height, Pitch, Roll and FOV

2026-07-23

AI Summary

Existing monocular depth estimation methods struggle to generalize to drone-captured aerial scenes due to the dynamic variations in camera pose—including altitude, pitch, roll, and field of view—which result in complex and multi-scale depth distributions. To address this challenge, this work proposes the DAPM framework, the first monocular depth estimation approach specifically designed for drone imagery. DAPM establishes a geometric mapping between viewing angles and observation distances and introduces an Ideal Ground Depth (IGD) module to provide dense pose-aware supervision. Additionally, a coarse-to-fine Progressive Quantized Binning (PQB) module enhances estimation robustness. Evaluated on the newly introduced UAPD dataset, the proposed method achieves state-of-the-art performance on both depth estimation and camera pose prediction, significantly outperforming existing approaches.

Abstract

Monocular depth estimation is a fundamental prerequisite for 3D reconstruction and autonomous navigation in Unmanned Aerial Vehicles (UAVs). In practical deployments, UAVs operate under highly dynamic camera poses characterized by continuous variations in height, pitch, roll, and field of view (FOV). Existing monocular depth estimation methods frequently fail to generalize across such diverse perspectives and the expansive scale of depth distributions inherent in aerial scenes. To address these challenges, we establish a quantitative representation of UAV viewing angles through rigorous theoretical analysis, deriving the geometric correspondence between viewing angles and view distances using the ground plane as a reference for observation. Building upon this, we propose Depth Estimation for Any Perspectives Model (DAPM), representing the first monocular framework specifically designed for UAV aerial imagery to jointly estimate camera pose and depth under continuously varying viewpoints. Specifically, we introduce an Ideal Ground Depth (IGD) module that leverages the derived geometric relationships between UAV perspectives and view distances to implement dense camera-pose supervision and enhance depth features. And we further develop a coarse-to-fine Progressive Quantization Bins (PQB) module. By incorporating progressive supervision and hierarchical quantization bins, the PQB module enables robust estimation in complex UAV aerial imagery. To evaluate the proposed framework, we present the UAV Any Perspectives Depth (UAPD) dataset, featuring comprehensive and continuous distributions of pose parameters. Experimental results on UAPD demonstrate that DAPM achieves state-of-the-art performance across both depth and camera-pose estimation metrics. The source code and datasets are available at: https://github.com/ThisIsLT/DAPM.

Problem

• monocular depth estimation
• UAV
• camera pose
• viewpoint variation
• aerial imagery

Innovation

• monocular depth estimation
• UAV
• camera pose estimation
• geometric correspondence
• progressive quantization