Metraipolis › archive › dc_efcf950778c2

METRIC-GS: Selective Metric-Scale Estimation for 3D Gaussian Splatting — arXiv:2611.06020

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.06020
License (as archived): CC0-1.0
Archived: 2026-11-05T18:29:51.923Z
SHA-256 of the archived text: 285a51b79497bcf7549be6b6bd0e6a50a55b4296e1b02159c243e25958f6b653
Stable URL of this page: https://metraipolis.com/documento/dc_efcf950778c2

How to cite

METRIC-GS: Selective Metric-Scale Estimation for 3D Gaussian Splatting — arXiv:2611.06020 — arXiv (en), https://arxiv.org/abs/2611.06020 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_efcf950778c2 (Metraipolis archive dc_efcf950778c2, sha256 285a51b79497bcf7549be6b6bd0e6a50a55b4296e1b02159c243e25958f6b653)

BibTeX

@misc{dcefcf950778c2,
  title = {METRIC-GS: Selective Metric-Scale Estimation for 3D Gaussian Splatting — arXiv:2611.06020},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06020},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_efcf950778c2; sha256 285a51b79497bcf7549be6b6bd0e6a50a55b4296e1b02159c243e25958f6b653},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06020. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A 3D Gaussian Splatting (3DGS) reconstruction inherits arbitrary units from structure-from-motion, so it cannot be measured or used to place AR content until someone supplies a scale. Both standard recipes are fragile on real captures: on five indoor scenes with tape-measured ceilings, a quantile floor-to-ceiling heuristic errs by 27% and metric-depth alignment by 35-71% across three networks. We present METRIC-GS, a selective scale estimator for real indoor photographs: it reads the scale off the reconstruction's own semantic content and, just as importantly, refuses when the evidence is thin. A frozen 2D teacher labels Gaussians by visibility-aware voting; instance-level size priors for architectural and furniture classes (doors, tables, the floor-to-ceiling gap) are fused by a robust maximum-likelihood step; and an inlier-mass test turns thin evidence into an explicit abstention that doubles as a router to a heavyweight metric model. On 47 ScanNet++ scenes with laser ground truth, with a configuration frozen before public evaluation, the estimator alone cuts the heuristic's mean error from 21.1% to 16.6% (9.3% on the 28 scenes it acts on) at ~11 s per scene. MASt3R remains the more accurate standalone estimator (9.9%), but routing only our refusals to it matches running it everywhere with 60% fewer invocations; this selective hybrid is the configuration we advocate. Visibility-aware voting raises the scenes the estimator can act on from 16 to 28 at unchanged deployed accuracy. Applied unchanged to 13 phone and drone captures of our own, on which MASt3R fails its own registration gate 12 times, the system improves all five captures it acts on and degrades none. We also report that a current feed-forward metric model scores 2.3% on a benchmark inside its training mixture and 28-35% on captures it has never seen: a published metric-scale number is a best case, not a deployment estimate.

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/2611.06020 — 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 2026-11-05T18:19:49.046Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).