Metraipolis › archive › dc_d2298afee07e

Budgeted-GS: Real-Time Large-Scale Gaussian Splatting via Factoring LOD — arXiv:2610.03162

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.03162
License (as archived)
CC0-1.0
Archived
2026-10-06T09:09:37.090Z
SHA-256 of the archived text
7a170fcb85326f18cb52e69d8311a3956931158008d5d81a08d5efb2a30d78df
Stable URL of this page
https://metraipolis.com/documento/dc_d2298afee07e

How to cite

Budgeted-GS: Real-Time Large-Scale Gaussian Splatting via Factoring LOD — arXiv:2610.03162 — arXiv (en), https://arxiv.org/abs/2610.03162 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d2298afee07e (Metraipolis archive dc_d2298afee07e, sha256 7a170fcb85326f18cb52e69d8311a3956931158008d5d81a08d5efb2a30d78df)
BibTeX
@misc{dcd2298afee07e,
  title = {Budgeted-GS: Real-Time Large-Scale Gaussian Splatting via Factoring LOD — arXiv:2610.03162},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.03162},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d2298afee07e; sha256 7a170fcb85326f18cb52e69d8311a3956931158008d5d81a08d5efb2a30d78df},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.03162. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

3D Gaussian Splatting achieves excellent visual quality with real-time rendering, but at the scale of entire cities it does not fit: a trained model carries millions of primitives and gigabytes of memory, and real-time rendering at high quality on a consumer GPU remains out of reach. We introduce Budgeted-GS, a post-hoc method that turns any trained 3DGS model into a factoring tree, a multi-resolution hierarchy of moment-matched aggregates. After a construction pass of a few seconds, a single quality parameter selects, for each view, the level of detail that fits the memory of the target device, so the same city-scale model serves GPUs with widely different memory capacities. When a new scene is to be trained, the same theory applies: instead of growing a full-sized model and compressing it afterwards, budget-centered training first measures how many primitives the scene needs and then trains the model directly at that size, avoiding the wasted effort of optimizing primitives that are later discarded. Both methods are grounded in a measurable capacity floor, a budget-error law derived from optimal transport in phase space; selection rules certified by recent covering theorems decide which primitives are redundant. The floor answers how many primitives a scene actually needs and how many can safely be given up. We validate the floor on 13 public scenes under a preregistered protocol, and exercise both methods from object scenes to an official city capture, rendering it at native 1920x1080, full SH, in real time on one consumer GPU.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.CV).
Categorie arXiv: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.03162 — 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 2026-10-06T08:21:44.304Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).