Metraipolis › archive › dc_44dcd5dd282d

SLAMFormer-$\infty$: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing — arXiv:2608.03429

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.03429
License (as archived): CC0-1.0
Archived: 2026-10-31T12:58:27.241Z
SHA-256 of the archived text: cc19422953c07796f210e610e350c5457ae98077baf3f1090d5253a9b674bcb7
Stable URL of this page: https://metraipolis.com/documento/dc_44dcd5dd282d

How to cite

SLAMFormer-$\infty$: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing — arXiv:2608.03429 — arXiv (en), https://arxiv.org/abs/2608.03429 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44dcd5dd282d (Metraipolis archive dc_44dcd5dd282d, sha256 cc19422953c07796f210e610e350c5457ae98077baf3f1090d5253a9b674bcb7)

BibTeX

@misc{dc44dcd5dd282d,
  title = {SLAMFormer-$infty$: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing — arXiv:2608.03429},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03429},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44dcd5dd282d; sha256 cc19422953c07796f210e610e350c5457ae98077baf3f1090d5253a9b674bcb7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03429. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce the Infinite SLAM Transformer (SLAMFormer-$\infty$), the first geometric transformer capable of supporting both long-range frontend and backend processing without an explicit distance bound. Instead of relying on a first-frame-anchored formulation, SLAMFormer-$\infty$ employs memory conditions to define flexible coordinate systems and scales for input frames, enabling more expressive structural conditioning. Built upon this formulation, the frontend preserves efficient local computation, while the backend jointly optimizes long-range trajectories and scene geometry in a globally consistent manner. Experimental results demonstrate that SLAMFormer-$\infty$ achieves superior or highly competitive performance in both trajectory estimation and scene reconstruction across large-scale datasets. Notably, SLAMFormer-$\infty$ generalizes to extremely long trajectories, successfully operating on sequences exceeding $17\mathrm{km}$.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.03429 — 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 2026-10-31T12:45:33.251Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).