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 synthesize a reconstructed view. We establish a self-supervised learning objective by comparing the synthesized view with the actual one. During training, we supervise both pose estimation and image synthesis, while at test time, we optimize the self-supervised objective. In addition, we introduce a regularization loss to prevent solutions that are not consistent with the keypoint structure of the spacecraft.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

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




    Erscheinungsdatum :

    01.10.2024


    Format / Umfang :

    6345110 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Kalman-based continuous pose estimation network for spacecraft

    Zhou, Rui / Qi, Naiming / Jia, Shuanli et al. | SPIE | 2024


    Spacecraft Pose Estimation Dataset (SPEED)

    Posso, Julien | DataCite | 2024


    Spacecraft Pose Estimation Based on Unsupervised Domain Adaptation and on a 3D-Guided Loss Combination

    Pérez-Villar, Juan Ignacio Bravo / García-Martín, Álvaro / Bescós, Jesús | ArXiv | 2022

    Freier Zugriff