Metraipolis › archive › dc_bf071037d283

OctreeSplat: Hierarchical Octree-Guided Feed-Forward Gaussian Splatting — arXiv:2611.02658

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02658
License (as archived)
CC0-1.0
Archived
2026-11-03T18:55:04.738Z
SHA-256 of the archived text
020cd518f52cedcd36f3edbff9cb21f5ac0407fc1f2da46166c3f2c0f5155add
Stable URL of this page
https://metraipolis.com/documento/dc_bf071037d283

How to cite

OctreeSplat: Hierarchical Octree-Guided Feed-Forward Gaussian Splatting — arXiv:2611.02658 — arXiv (en), https://arxiv.org/abs/2611.02658 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf071037d283 (Metraipolis archive dc_bf071037d283, sha256 020cd518f52cedcd36f3edbff9cb21f5ac0407fc1f2da46166c3f2c0f5155add)
BibTeX
@misc{dcbf071037d283,
  title = {OctreeSplat: Hierarchical Octree-Guided Feed-Forward Gaussian Splatting — arXiv:2611.02658},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02658},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf071037d283; sha256 020cd518f52cedcd36f3edbff9cb21f5ac0407fc1f2da46166c3f2c0f5155add},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02658. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

3D Gaussian Splatting (3DGS) has shown considerable potential for novel view synthesis (NVS) and 3D reconstruction. Feed-forward methods avoid costly per-scene optimization, but fixed image or spatial resolutions limit their ability to allocate primitives according to local complexity. We present OctreeSplat, a hierarchical octree-guided feed-forward Gaussian splatting. OctreeSplat extracts multi-view features and geometric priors from a frozen visual foundation model (VFM), constructs a hierarchical octree, and predicts densification scores. The resulting representation allocates Gaussian primitives at spatially varying densities according to local complexity. Stochastic solids volume rendering improves depth rendering, strengthens geometric supervision, and supports surface reconstruction. When camera parameters are available, an optional test-time optimization (TTO) module improves agreement between predicted and ground-truth parameters. Training updates only 76 million additional parameters and requires 35 GPU-hours. Experiments on Replica, TUM, Tanks and Temples, and DTU demonstrate competitive RGB view synthesis, depth synthesis, and surface reconstruction. OctreeSplat reduces the number of Gaussian primitives while maintaining high reconstruction quality.

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/2611.02658 — 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 2026-11-03T18:16:53.010Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).