arXiv:2512.09792v1 Announce Type: new 
Abstract: Estimating the 6-degrees-of-freedom (6DoF) pose of a spacecraft from a single image is critical for autonomous operations like in-orbit servicing and space debris removal. Existing state-of-the-art methods often rely on iterative Perspective-n-Point (PnP)-based algorithms, which are computationally intensive and ill-suited for real-time deployment on resource-constrained edge devices. To overcome these limitations, we propose FastPose-ViT, a Vision Transformer (ViT)-based architecture that directly regresses the 6DoF pose. Our approach processes cropped images from object bounding boxes and introduces a novel mathematical formalism to map these localized predictions back to the full-image scale. This formalism is derived from the principles of projective geometry and the concept of "apparent rotation", where the model predicts an apparent rotation matrix that is then corrected to find the true orientation. We demonstrate that our method outperforms other non-PnP strategies and achieves performance competitive with state-of-the-art PnP-based techniques on the SPEED dataset. Furthermore, we validate our model's suitability for real-world space missions by quantizing it and deploying it on power-constrained edge hardware. On the NVIDIA Jetson Orin Nano, our end-to-end pipeline achieves a latency of ~75 ms per frame under sequential execution, and a non-blocking throughput of up to 33 FPS when stages are scheduled concurrently.

تم تقديم FastPose-ViT، وهي بنية جديدة تعتمد على المحولات البصرية، لتقدير وضع المركبات الفضائية في الوقت الحقيقي، مما يسمح بالتراجع المباشر لوضع 6 درجات من الحرية من صورة واحدة. تهدف هذه الطريقة إلى تحسين العمليات المستقلة مثل الخدمة في المدار وإزالة الحطام الفضائي من خلال التغلب على قيود الخوارزميات التقليدية التي تتطلب حسابات مكثفة.

FastPose-ViT, una nueva arquitectura basada en Vision Transformers, ha sido presentada para la estimación en tiempo real de la pose de naves espaciales, permitiendo la regresión directa de la pose de 6 grados de libertad a partir de una sola imagen. Este método busca mejorar las operaciones autónomas como el servicio en órbita y la eliminación de desechos espaciales al superar las limitaciones de los algoritmos tradicionales que requieren mucho cálculo.

FastPose-ViT, une nouvelle architecture basée sur les Vision Transformers, a été introduite pour l'estimation en temps réel de la pose des engins spatiaux, permettant la régression directe de la pose à 6 degrés de liberté d'une image unique. Cette méthode vise à améliorer les opérations autonomes telles que le service en orbite et l'élimination des débris spatiaux en surmontant les limitations des algorithmes traditionnels intensifs en calcul.

FastPose-ViT, a new Vision Transformer-based architecture, has been introduced for real-time spacecraft pose estimation, allowing for the direct regression of a spacecraft's 6-degrees-of-freedom pose from a single image. This method aims to enhance autonomous operations such as in-orbit servicing and space debris removal by overcoming the limitations of traditional computationally intensive algorithms.

FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation

Was this article worth reading? Share it

Rendora AI

Fakeface

HomeVisualizer.AI

Video Face Swap AI

Uwear

Attentive AI

Ready to build your own newsroom?