Metraipolis › archive › dc_f387f87ae511

Rate-Distortion Adaptive Primitive Selection for Omnidirectional Gaussian Splatting — arXiv:2609.34367

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.34367
License (as archived): CC0-1.0
Archived: 2026-10-07T23:52:05.822Z
SHA-256 of the archived text: f1017943ec08adf9e05844547526406564bfcb48b4e192c07218449b96f38010
Stable URL of this page: https://metraipolis.com/documento/dc_f387f87ae511

How to cite

Rate-Distortion Adaptive Primitive Selection for Omnidirectional Gaussian Splatting — arXiv:2609.34367 — arXiv (en), https://arxiv.org/abs/2609.34367 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f387f87ae511 (Metraipolis archive dc_f387f87ae511, sha256 f1017943ec08adf9e05844547526406564bfcb48b4e192c07218449b96f38010)

BibTeX

@misc{dcf387f87ae511,
  title = {Rate-Distortion Adaptive Primitive Selection for Omnidirectional Gaussian Splatting — arXiv:2609.34367},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34367},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f387f87ae511; sha256 f1017943ec08adf9e05844547526406564bfcb48b4e192c07218449b96f38010},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34367. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learned image codecs (LICs) achieve high reconstruction quality, but their decoding speed is often insufficient for immersive virtual reality (VR). Gaussian splatting (GS) codecs render much faster, yet still lag in reconstruction quality and typically decide primitive allocation without considering the coding cost of each primitive. We introduce OIC-GS, an omnidirectional GS codec with a new hierarchical HEALPix primitive grid representation. Gaussian primitives are anchored at predefined spherical locations, eliminating explicit coordinate coding. Finer levels refine their coarser ancestors, naturally supporting coarse-to-fine reconstruction and layered transmission. The predefined grid also enables efficient viewport decoding by selecting only view-relevant primitives. We further introduce a lightweight entropy model for quantized primitives and optimize the codec under a spherical rate-distortion objective. Primitives with insufficient rate-distortion benefit are automatically removed when their quantized opacity becomes zero, allowing OIC-GS to adapt both primitive density and level of detail without a fixed primitive budget. A single bitstream supports full-sphere, viewport-dependent, and progressive decoding. The first viewport reaches final quality after decoding only 52% of the bitstream, and is then rendered at 1,270 FPS. On a 100-image omnidirectional benchmark, OIC-GS outperforms all evaluated GS codecs, reducing WS-PSNR BD-rate by 49.6% over GaussianImage++ and 68.6% over SGI, which uses a learned entropy model.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.34367 — 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 2026-10-07T23:29:27.357Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).