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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pérez-Villar, Juan Ignacio Bravo, García-Martín, Álvaro, Bescós, Jesús, SanMiguel, Juan C.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912060575580160
author Pérez-Villar, Juan Ignacio Bravo
García-Martín, Álvaro
Bescós, Jesús
SanMiguel, Juan C.
author_facet Pérez-Villar, Juan Ignacio Bravo
García-Martín, Álvaro
Bescós, Jesús
SanMiguel, Juan C.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04298
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesis
Pérez-Villar, Juan Ignacio Bravo
García-Martín, Álvaro
Bescós, Jesús
SanMiguel, Juan C.
Computer Vision and Pattern Recognition
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.
title Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.04298