A large-scale, physically-based synthetic dataset for satellite pose estimation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Velkei, Szabolcs, Goldschmidt, Csaba, Vass, Károly
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911007056592896
author Velkei, Szabolcs
Goldschmidt, Csaba
Vass, Károly
author_facet Velkei, Szabolcs
Goldschmidt, Csaba
Vass, Károly
contents The Deep Learning Visual Space Simulation System (DLVS3) introduces a novel synthetic dataset generator and a simulation pipeline specifically designed for training and testing satellite pose estimation solutions. This work introduces the DLVS3-HST-V1 dataset, which focuses on the Hubble Space Telescope (HST) as a complex, articulated target. The dataset is generated using advanced real-time and offline rendering technologies, integrating high-fidelity 3D models, dynamic lighting (including secondary sources like Earth reflection), and physically accurate material properties. The pipeline supports the creation of large-scale, richly annotated image sets with ground-truth 6-DoF pose and keypoint data, semantic segmentation, depth, and normal maps. This enables the training and benchmarking of deep learning-based pose estimation solutions under realistic, diverse, and challenging visual conditions. The paper details the dataset generation process, the simulation architecture, and the integration with deep learning frameworks, and positions DLVS3 as a significant step toward closing the domain gap for autonomous spacecraft operations in proximity and servicing missions.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12782
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A large-scale, physically-based synthetic dataset for satellite pose estimation
Velkei, Szabolcs
Goldschmidt, Csaba
Vass, Károly
Computer Vision and Pattern Recognition
68U10 (Primary), 68T45 (Secondary)
I.4.8; I.2.10
The Deep Learning Visual Space Simulation System (DLVS3) introduces a novel synthetic dataset generator and a simulation pipeline specifically designed for training and testing satellite pose estimation solutions. This work introduces the DLVS3-HST-V1 dataset, which focuses on the Hubble Space Telescope (HST) as a complex, articulated target. The dataset is generated using advanced real-time and offline rendering technologies, integrating high-fidelity 3D models, dynamic lighting (including secondary sources like Earth reflection), and physically accurate material properties. The pipeline supports the creation of large-scale, richly annotated image sets with ground-truth 6-DoF pose and keypoint data, semantic segmentation, depth, and normal maps. This enables the training and benchmarking of deep learning-based pose estimation solutions under realistic, diverse, and challenging visual conditions. The paper details the dataset generation process, the simulation architecture, and the integration with deep learning frameworks, and positions DLVS3 as a significant step toward closing the domain gap for autonomous spacecraft operations in proximity and servicing missions.
title A large-scale, physically-based synthetic dataset for satellite pose estimation
topic Computer Vision and Pattern Recognition
68U10 (Primary), 68T45 (Secondary)
I.4.8; I.2.10
url https://arxiv.org/abs/2506.12782