Metraipolis › archive › dc_2520c8ff55c5

Hierarchical Incremental Beta Splatting for Online Reconstruction — arXiv:2611.08288

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08288
License (as archived)
CC0-1.0
Archived
2026-11-06T14:53:45.350Z
SHA-256 of the archived text
366fff76779015e3a20473b5c7e105518669b40bf9e22ccb9c57474118ebc157
Stable URL of this page
https://metraipolis.com/documento/dc_2520c8ff55c5

How to cite

Hierarchical Incremental Beta Splatting for Online Reconstruction — arXiv:2611.08288 — arXiv (en), https://arxiv.org/abs/2611.08288 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2520c8ff55c5 (Metraipolis archive dc_2520c8ff55c5, sha256 366fff76779015e3a20473b5c7e105518669b40bf9e22ccb9c57474118ebc157)
BibTeX
@misc{dc2520c8ff55c5,
  title = {Hierarchical Incremental Beta Splatting for Online Reconstruction — arXiv:2611.08288},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08288},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2520c8ff55c5; sha256 366fff76779015e3a20473b5c7e105518669b40bf9e22ccb9c57474118ebc157},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08288. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Online 3D Gaussian Splatting reconstructs a scene during capture: each keyframe spawns primitives once and refines them for only a few dozen iterations, leaving little chance to fix poor initialization or missing detail. Gaussians are also inherently soft, needing many overlaps for solid surfaces. We present Hierarchical Incremental Beta Splatting (HIBS), which brings beta kernels to incremental reconstruction. Their shape parameter interpolates between a soft, Gaussian-like profile and a flat-topped, near-opaque surfel, acting as a confidence dial for geometry. Our confidence-aware spawning uses geometric observability and multi-view depth agreement to initialize both opacity and shape, producing solid primitives where geometry is verifiable and soft, correctable primitives where it is not. As online densification, error-driven relocation recycles stale primitives into photometric-error hotspots. Bounded beta kernel support enables exact tile culling and faster rasterization, and a closed-form, shape-preserving merging formulation provides a level-of-detail (LOD) hierarchy for fast optimization and real-time rendering. On Mip-NeRF 360 in the on-the-fly protocol, HIBS improves PSNR by up to 0.8 dB while reducing optimization time by up to 40%. Project page: this https URL

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) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2611.08288 — 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 2026-11-06T14:25:42.628Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).