Domain Generalization for In-Orbit 6D Pose Estimation
Authors:
- 1 November 2025
- journal article
- Published by American Institute of Aeronautics and Astronautics (AIAA) in Journal of Aerospace Information Systems
- Vol. 22 (11) , 938-947
Abstract
We address the problem of estimating the relative 6D pose, e.g., position and orientation, of a target spacecraft from a monocular image, a key capability for future autonomous rendezvous and proximity operations. Due to the difficulty of acquiring large sets of real images, spacecraft pose estimation networks are exclusively trained on synthetic ones. However, because those images do not capture the illumination conditions encountered in orbit, pose estimation networks face a domain gap problem, e.g., they do not generalize to real images. Our work introduces a method that bridges this domain gap. It relies on a novel, end-to-end, neural-based architecture as well as a novel learning strategy. This strategy improves the domain generalization abilities of the network through multitask learning and aggressive data augmentation policies, thereby enforcing the network to learn domain-invariant features. We demonstrate that our method effectively closes the domain gap, achieving state-of-the-art accuracy on the widespread SPEED+ dataset. Finally, ablation studies assess the impact of key components of our method on its generalization abilities.Keywords
All Related Versions
Funding Information
- Gouvernement Wallon
- Fonds De La Recherche Scientifique - FNRS
This publication has 24 references indexed in Scilit:
- Robust multi-task learning and online refinement for spacecraft pose estimation across domain gapAdvances In Space Research, 2023
- Leveraging neural network uncertainty in adaptive unscented Kalman Filter for spacecraft pose estimationAdvances In Space Research, 2023
- Fourier-based augmentation with applications to domain generalizationPattern Recognition, 2023
- Satellite Pose Estimation Competition 2021: Results and AnalysesActa Astronautica, 2023
- On-ground validation of a CNN-based monocular pose estimation system for uncooperative spacecraft: Bridging domain shift in rendezvous scenariosActa Astronautica, 2022
- Pose estimation and tracking of non-cooperative rocket bodies using Time-of-Flight camerasActa Astronautica, 2017
- A review of cooperative and uncooperative spacecraft pose determination techniques for close-proximity operationsProgress in Aerospace Sciences, 2017
- Stereovision-based pose and inertia estimation of unknown and uncooperative space objectsAdvances In Space Research, 2017
- RemoveDEBRIS: An in-orbit active debris removal demonstration missionActa Astronautica, 2016
- EPnP: An Accurate O(n) Solution to the PnP ProblemInternational Journal of Computer Vision, 2008