Saved in:
Bibliographic Details
Main Authors: Yang, Steven, Tian, Xiaoyu, Goel, Kshitij, Tabib, Wennie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.08159
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908528749314048
author Yang, Steven
Tian, Xiaoyu
Goel, Kshitij
Tabib, Wennie
author_facet Yang, Steven
Tian, Xiaoyu
Goel, Kshitij
Tabib, Wennie
contents This paper presents a methodology to predict metric depth from monocular RGB images and an inertial measurement unit (IMU). To enable collision avoidance during autonomous flight, prior works either leverage heavy sensors (e.g., LiDARs or stereo cameras) or data-intensive and domain-specific fine-tuning of monocular metric depth estimation methods. In contrast, we propose several lightweight zero-shot rescaling strategies to obtain metric depth from relative depth estimates via the sparse 3D feature map created using a visual-inertial navigation system. These strategies are compared for their accuracy in diverse simulation environments. The best performing approach, which leverages monotonic spline fitting, is deployed in the real-world on a compute-constrained quadrotor. We obtain on-board metric depth estimates at 15 Hz and demonstrate successful collision avoidance after integrating the proposed method with a motion primitives-based planner.
format Preprint
id arxiv_https___arxiv_org_abs_2509_08159
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Zero-Shot Metric Depth Estimation via Monocular Visual-Inertial Rescaling for Autonomous Aerial Navigation
Yang, Steven
Tian, Xiaoyu
Goel, Kshitij
Tabib, Wennie
Robotics
Artificial Intelligence
This paper presents a methodology to predict metric depth from monocular RGB images and an inertial measurement unit (IMU). To enable collision avoidance during autonomous flight, prior works either leverage heavy sensors (e.g., LiDARs or stereo cameras) or data-intensive and domain-specific fine-tuning of monocular metric depth estimation methods. In contrast, we propose several lightweight zero-shot rescaling strategies to obtain metric depth from relative depth estimates via the sparse 3D feature map created using a visual-inertial navigation system. These strategies are compared for their accuracy in diverse simulation environments. The best performing approach, which leverages monotonic spline fitting, is deployed in the real-world on a compute-constrained quadrotor. We obtain on-board metric depth estimates at 15 Hz and demonstrate successful collision avoidance after integrating the proposed method with a motion primitives-based planner.
title Zero-Shot Metric Depth Estimation via Monocular Visual-Inertial Rescaling for Autonomous Aerial Navigation
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2509.08159