Metraipolis › archive › dc_77bf3fd0ff19
QuARC-GS: Quantized Anchored Residual Coding for Compact Dynamic Scene Streaming with Gaussian Splatting — arXiv:2608.18285
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.18285
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:06:36.347Z
- SHA-256 of the archived text
a2f9561cebafd5b50a9c535cfaa4998d7cc84805390a37b41dbd4e7be2685836- Stable URL of this page
https://metraipolis.com/documento/dc_77bf3fd0ff19
How to cite
QuARC-GS: Quantized Anchored Residual Coding for Compact Dynamic Scene Streaming with Gaussian Splatting — arXiv:2608.18285 — arXiv (en), https://arxiv.org/abs/2608.18285 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_77bf3fd0ff19 (Metraipolis archive dc_77bf3fd0ff19, sha256 a2f9561cebafd5b50a9c535cfaa4998d7cc84805390a37b41dbd4e7be2685836)
BibTeX
@misc{dc77bf3fd0ff19,
title = {QuARC-GS: Quantized Anchored Residual Coding for Compact Dynamic Scene Streaming with Gaussian Splatting — arXiv:2608.18285},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.18285},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_77bf3fd0ff19; sha256 a2f9561cebafd5b50a9c535cfaa4998d7cc84805390a37b41dbd4e7be2685836},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18285. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
3D scene representation techniques such as neural radiance fields (NeRFs) and Gaussian splatting have made substantial progress in novel view synthesis, achieving high-quality renderings from arbitrary view angles. More recently, such techniques have been extended to dynamic 3D scenes; however, achieving sustainable online free-viewpoint video (FVV) streaming remains challenging, especially for longer videos, due to significant storage demands of detailed scene representations and high reconstruction/rendering speed needs. To address these challenges, we propose Quantized Anchored Residual Coding Gaussian Streaming (QuARC-GS), a quantization-aware 4D scene optimization framework for online dynamic scene reconstruction that achieves ultra-high compression while maintaining reconstruction speed and quality. QuARC-GS represents a scene using a single canonical frame and highly compressed per-frame residuals. Specifically, we compress each residual through two complementary strategies targeting motion, appearance, and densification. We introduce quantization-aware anchor deformation, which suppresses insignificant motion updates while preserving meaningful deformations, maintaining reconstruction quality under low-storage streaming. Furthermore, we design a change-gated densification strategy that allocates new Gaussians only in regions exhibiting genuine temporal changes, effectively eliminating redundant appearance updates and reducing storage overhead. Extensive experiments on widely used datasets demonstrate that QuARC-GS enables competitive reconstruction quality and training speed while cutting per-frame storage by up to 11$\times$ compared to the state-of-the-art. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-20 in cs.CV). Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.18285 — 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 2026-10-18T14:00:22.600Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).