Metraipolis › archive › dc_06a397fb3f4e

Vision Foundation Models with Synthetic-Only Training for Monocular Spacecraft Pose Estimation — arXiv:2609.26561

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.26561
License (as archived): CC0-1.0
Archived: 2026-10-08T16:39:44.470Z
SHA-256 of the archived text: 2830406236b79672851aab39f82e3ac699c04d293e90c322429c6124866f5c8d
Stable URL of this page: https://metraipolis.com/documento/dc_06a397fb3f4e

How to cite

Vision Foundation Models with Synthetic-Only Training for Monocular Spacecraft Pose Estimation — arXiv:2609.26561 — arXiv (en), https://arxiv.org/abs/2609.26561 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_06a397fb3f4e (Metraipolis archive dc_06a397fb3f4e, sha256 2830406236b79672851aab39f82e3ac699c04d293e90c322429c6124866f5c8d)

BibTeX

@misc{dc06a397fb3f4e,
  title = {Vision Foundation Models with Synthetic-Only Training for Monocular Spacecraft Pose Estimation — arXiv:2609.26561},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26561},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_06a397fb3f4e; sha256 2830406236b79672851aab39f82e3ac699c04d293e90c322429c6124866f5c8d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26561. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present an improvement on previous spacecraft pose estimation architectures that results in the lowest published mean rotation errors we know of on the SPEED+ lightbox and sunlamp test sets for a known, non-cooperative spacecraft. By using a previously established heatmap-based pose estimation architecture and adapting a large self-supervised ViT foundation model (DINOv3) in place of the smaller convolutional and ViT encoders of previous work, we show that pose estimation accuracy improves from 300M to 840M parameters with no saturation yet observed. We also evaluate our 840M model on a Jetson Orin NX 16GB, measuring single-pass network inference at 133.8 ms per crop with a board draw of 32.0 W. These measurements demonstrate embedded inference feasibility on a processor family with orbital flight heritage. Our resulting model outperforms previous models across lightbox and sunlamp domains while training only on synthetic data. Our best model, using DINOv3 840M adapted with LoRA as the encoder (rank 64, three-seed ensemble with four-rotation test-time augmentation), results in $1.56^\circ$ mean rotation error on sunlamp and $1.17^\circ$ on lightbox, compared to the previous best mean rotation errors we know of on these test sets, $2.66^\circ$ and $1.75^\circ$ by EagerNet.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.26561 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T15:56:18.211Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).