Metraipolis › archive › dc_fbb27b1de61d
MarsRecon: Self-Supervised and Multimodal Surface Representations for Mars — arXiv:2609.22379
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22379
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T21:59:09.520Z
- SHA-256 of the archived text
f6c859924503de12ea91b7d9d8a57ebd42d7812408340c5d7d5fc7c0751cf4be- Stable URL of this page
https://metraipolis.com/documento/dc_fbb27b1de61d
How to cite
MarsRecon: Self-Supervised and Multimodal Surface Representations for Mars — arXiv:2609.22379 — arXiv (en), https://arxiv.org/abs/2609.22379 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fbb27b1de61d (Metraipolis archive dc_fbb27b1de61d, sha256 f6c859924503de12ea91b7d9d8a57ebd42d7812408340c5d7d5fc7c0751cf4be)
BibTeX
@misc{dcfbb27b1de61d,
title = {MarsRecon: Self-Supervised and Multimodal Surface Representations for Mars — arXiv:2609.22379},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22379},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fbb27b1de61d; sha256 f6c859924503de12ea91b7d9d8a57ebd42d7812408340c5d7d5fc7c0751cf4be},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22379. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
High-resolution orbital imagery offers a rich record of the Martian surface, but sparse geological labels limit supervised representation learning. We present MarsRecon, a geospatially aware pipeline for learning visual and multimodal representations from HiRISE observations of Olympus Mons. The pipeline calibrates NASA Planetary Data System products, extracts valid georeferenced patches, and trains a masked autoencoder on unlabeled imagery. Increasing input resolution and filtering invalid tokens reduced held-out reconstruction loss from 0.1751 to 0.1342 in the principal Stage A model series. We then freeze the visual encoder and align its features with observation text, coordinates, and local--global image context. The strongest current local-primary model achieves image-to-text recall@10 of 0.3787, text-to-image recall@10 of 0.9161, and local-to-global recall@10 of 0.4350 on the held-out test split. These results establish a working Mars-specific pretraining and retrieval pipeline; further crop-overlap controls and downstream geological evaluations are needed to assess the broader utility of its embeddings. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.22379 — 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 2026-10-09T21:45:20.790Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).