TanDepth: Leveraging Global DEMs for Metric Monocular Depth Estimation in UAVs

TL;DR

TanDepth introduces a scale recovery method that leverages global DEMs to convert relative monocular depth estimates into metric depths for UAVs, addressing the challenges of data scarcity and scale ambiguity.

Contribution

The paper presents a novel scale recovery approach using GDEM data for monocular depth estimation in UAVs, adaptable to various models and evaluated on real-world scenes.

Findings

Effective scale recovery from relative depth estimates.

Improved metric depth accuracy in UAV scenes.

Enhanced dataset for aerial depth research.

Abstract

Aerial scene understanding systems face stringent payload restrictions and must often rely on monocular depth estimation for modeling scene geometry, which is an inherently ill-posed problem. Moreover, obtaining accurate ground truth data required by learning-based methods raises significant additional challenges in the aerial domain. Self-supervised approaches can bypass this problem, at the cost of providing only up-to-scale results. Similarly, recent supervised solutions which make good progress towards zero-shot generalization also provide only relative depth values. This work presents TanDepth, a practical scale recovery method for obtaining metric depth results from relative estimations at inference-time, irrespective of the type of model generating them. Tailored for Unmanned Aerial Vehicle (UAV) applications, our method leverages sparse measurements from Global Digital Elevation Models (GDEM) by projecting them to the camera view using extrinsic and intrinsic information. An adaptation to the Cloth Simulation Filter is presented, which allows selecting ground points from the estimated depth map to then correlate with the projected reference points. We evaluate and compare our method against alternate scaling methods adapted for UAVs, on a variety of real-world scenes. Considering the limited availability of data for this domain, we construct and release a comprehensive, depth-focused extension to the popular UAVid dataset to further research.