Metraipolis › archive › dc_24e778baf86f

Mamba3R: Fixed-Capacity Selective State Memory for Long-Sequence 3D Reconstruction — arXiv:2611.04221

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04221
License (as archived)
CC0-1.0
Archived
2026-11-04T12:56:09.398Z
SHA-256 of the archived text
6b2094d75d84e4320a4d0e566023358ebcaea30c72d9442bda95090f587869d3
Stable URL of this page
https://metraipolis.com/documento/dc_24e778baf86f

How to cite

Mamba3R: Fixed-Capacity Selective State Memory for Long-Sequence 3D Reconstruction — arXiv:2611.04221 — arXiv (en), https://arxiv.org/abs/2611.04221 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_24e778baf86f (Metraipolis archive dc_24e778baf86f, sha256 6b2094d75d84e4320a4d0e566023358ebcaea30c72d9442bda95090f587869d3)
BibTeX
@misc{dc24e778baf86f,
  title = {Mamba3R: Fixed-Capacity Selective State Memory for Long-Sequence 3D Reconstruction — arXiv:2611.04221},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04221},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_24e778baf86f; sha256 6b2094d75d84e4320a4d0e566023358ebcaea30c72d9442bda95090f587869d3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04221. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Streaming 3D reconstruction must maintain geometric quality over long inputs within a fixed GPU budget. A pretrained recurrent model provides bounded state, but freezing its backbone also fixes its learned state-observation interactions. We introduce Mamba3R, a jointly designed state-memory adapter that provides a trainable adaptation path without updating the backbone or task heads. A selective state-space mixer jointly transforms native state features and a fixed-capacity auxiliary memory, explicit read and write paths carry information across frames, and a decomposed feedback path regulates what the added memory feeds back. Only 1.28 million adapter parameters are trained. Under a shared periodic-reset protocol, it lowers trajectory error and improves accumulated surface and depth accuracy over recurrent baselines on public indoor and outdoor datasets and robot-recorded traversals, gaining up to 40 percent on one metric. Matched comparisons support both the choice of the mixing operator and the utility of carrying the auxiliary memory across frames. Allocated memory remains unchanged and throughput moves by at most 1.4 percent from one to two thousand frames. Replaying its recorded traversals offline, the platform's RTX 4060 averages 11.7 frames per second within 5.1 GiB with the same checkpoint, a mean throughput covering the 10 Hz sensor rate.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.04221 — 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 2026-11-04T12:33:47.112Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).