Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesis

TL;DR

This paper introduces a test-time adaptation method for spacecraft pose estimation that uses sequential image features and self-supervised learning to improve accuracy in real operational conditions, addressing synthetic-to-real domain gaps.

Contribution

It proposes a novel test-time adaptation framework leveraging temporal redundancy and self-supervised learning for keypoint-based spacecraft pose estimation.

Findings

Improved pose estimation accuracy in real-world conditions.

Effective view synthesis using self-supervised learning.

Regularisation maintains keypoint structure consistency.

Abstract

Due to the difficulty of replicating the real conditions during training, supervised algorithms for spacecraft pose estimation experience a drop in performance when trained on synthetic data and applied to real operational data. To address this issue, we propose a test-time adaptation approach that leverages the temporal redundancy between images acquired during close proximity operations. Our approach involves extracting features from sequential spacecraft images, estimating their poses, and then using this information to synthesise a reconstructed view. We establish a self-supervised learning objective by comparing the synthesised view with the actual one. During training, we supervise both pose estimation and image synthesis, while at test-time, we optimise the self-supervised objective. Additionally, we introduce a regularisation loss to prevent solutions that are not consistent with the keypoint structure of the spacecraft. Our code is available at: https://github.com/JotaBravo/spacecraft-tta.