Metraipolis › archive › dc_cca4d55ea1e1

ResStreamGS: Residual-Sensitive Dual-Stream Gaussian Splatting for Mobile Volumetric Video Streaming — arXiv:2610.21121

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21121
License (as archived)
CC0-1.0
Archived
2026-10-16T10:39:35.479Z
SHA-256 of the archived text
935fff4e253470d43cbc961c60f23f04d10461bca18c4dfc181e459250065151
Stable URL of this page
https://metraipolis.com/documento/dc_cca4d55ea1e1

How to cite

ResStreamGS: Residual-Sensitive Dual-Stream Gaussian Splatting for Mobile Volumetric Video Streaming — arXiv:2610.21121 — arXiv (en), https://arxiv.org/abs/2610.21121 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cca4d55ea1e1 (Metraipolis archive dc_cca4d55ea1e1, sha256 935fff4e253470d43cbc961c60f23f04d10461bca18c4dfc181e459250065151)
BibTeX
@misc{dccca4d55ea1e1,
  title = {ResStreamGS: Residual-Sensitive Dual-Stream Gaussian Splatting for Mobile Volumetric Video Streaming — arXiv:2610.21121},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21121},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cca4d55ea1e1; sha256 935fff4e253470d43cbc961c60f23f04d10461bca18c4dfc181e459250065151},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21121. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-time mobile volumetric video enables immersive free-viewpoint experiences, but delivering high-quality 3D content under constrained bandwidth and computation remains challenging. Recent 3D Gaussian Splatting (3DGS) systems, such as V$^3$, enable efficient mobile streaming by encoding time-varying Gaussian attributes with commodity video codecs and hardware decoding. However, existing pipelines treat all Gaussians as frame-varying signals, which is poorly suited to full-scene content where large portions remain temporally stable. Our empirical study shows that frame-wise adaptation and video coding of all Gaussians cause quality degradation in complex full-scene content, particularly in temporally stable regions. To address this issue, we propose ResStreamGS, a residual-sensitive dual-stream framework that processes Gaussians according to their temporal behavior. ResStreamGS identifies residual-sensitive primitives through lightweight probe adaptation and reuses stable Gaussians within each Group of Pictures (GOP). Stable Gaussians are transmitted once per GOP, while only residual-sensitive Gaussians remain in the frame-wise hardware-decodable video stream. Experiments on complex full-scene volumetric videos show that ResStreamGS improves post-codec PSNR by 7.51--8.35~dB over a controlled V$^3$-style all-Gaussians baseline, reduces amortized payload by up to 56.5%, and achieves 30.883~FPS on a Qualcomm Snapdragon 778G platform.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.21121 — 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 2026-10-16T08:52:02.757Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).