Metraipolis › archive › dc_f5a421977bcf

3D Point Tracking with State Space Models — arXiv:2609.34035

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34035
License (as archived)
CC0-1.0
Archived
2026-10-07T22:40:18.167Z
SHA-256 of the archived text
d4c6a157bb337bbc162de64bbee33f8b992d0fdff9e254b76a198b075ffb2f8a
Stable URL of this page
https://metraipolis.com/documento/dc_f5a421977bcf

How to cite

3D Point Tracking with State Space Models — arXiv:2609.34035 — arXiv (en), https://arxiv.org/abs/2609.34035 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f5a421977bcf (Metraipolis archive dc_f5a421977bcf, sha256 d4c6a157bb337bbc162de64bbee33f8b992d0fdff9e254b76a198b075ffb2f8a)
BibTeX
@misc{dcf5a421977bcf,
  title = {3D Point Tracking with State Space Models — arXiv:2609.34035},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34035},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f5a421977bcf; sha256 d4c6a157bb337bbc162de64bbee33f8b992d0fdff9e254b76a198b075ffb2f8a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34035. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tracking any point of a dynamic scene in metric 3D - in absolute meters, not up to an unknown scale - underpins 3D and 4D reconstruction, robot navigation, and autonomous driving, where decisions are made in meters, not pixels. Our objective is a 3D point tracker accurate in those absolute terms and operating within a single commodity GPU, pose-free, monocular budget. Our method rests on one observation: once a point's 2D image trajectory is fixed, the quantity that governs its metric accuracy is the depth along its pixel ray. Rather than learning tracking end-to-end, we therefore compose two frozen front-ends - dense optical flow for 2D correspondence and a monocular metric-depth network for the third dimension - and learn only the residual they cannot supply: that depth, refined by a compact state space model (Mamba-3) conditioned on appearance features (DINOv3). A state space model rather than the transformers the strongest 3D trackers adopt is what makes a single-GPU budget attainable: it summarises a track in a fixed-size recurrent state whose memory cost is constant in the number of frames, whereas attention requires a key-value cache that grows linearly with them. On the TAPVid-3D minival benchmark our best configuration attains the highest absolute metric accuracy among methods evaluated under identical conditions (mean metric Average Jaccard, 0.256), exceeding strong feed-forward trackers, while a companion analysis, reproduced with each competitor's own evaluator, explains why several published trackers lose most of their accuracy under this budget.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.34035 — 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 2026-10-07T22:14:28.806Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).