Metraipolis › archive › dc_9733f6950459

S$^2$GS: Structured Sparse Gaussian Streaming for Efficient Free-Viewpoint Video Reconstruction on Edge-IoT Devices — arXiv:2608.19639

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19639
License (as archived)
CC0-1.0
Archived
2026-10-18T12:04:36.615Z
SHA-256 of the archived text
71913adfa947dd0a45b6707710e55487863a95615f192dbdaad44385c44c28ce
Stable URL of this page
https://metraipolis.com/documento/dc_9733f6950459

How to cite

S$^2$GS: Structured Sparse Gaussian Streaming for Efficient Free-Viewpoint Video Reconstruction on Edge-IoT Devices — arXiv:2608.19639 — arXiv (en), https://arxiv.org/abs/2608.19639 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9733f6950459 (Metraipolis archive dc_9733f6950459, sha256 71913adfa947dd0a45b6707710e55487863a95615f192dbdaad44385c44c28ce)
BibTeX
@misc{dc9733f6950459,
  title = {S$^2$GS: Structured Sparse Gaussian Streaming for Efficient Free-Viewpoint Video Reconstruction on Edge-IoT Devices — arXiv:2608.19639},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19639},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9733f6950459; sha256 71913adfa947dd0a45b6707710e55487863a95615f192dbdaad44385c44c28ce},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19639. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Streaming reconstruction of Free-Viewpoint Videos (FVVs) supports immersive Internet of Things (IoT) services, such as telepresence and digital twin visualization. Existing methods suffer from high per-frame optimization time and large storage footprints, limiting deployment on resource-constrained Edge-IoT devices. To address these challenges, we propose Structured Sparse Gaussian Streaming (S$^2$GS), an FVV reconstruction framework that exploits structure-aware temporal sparsity to selectively update Gaussian residuals, enabling efficient streaming without compromising visual fidelity. In the spatial domain, a streaming octree hierarchically organizes Gaussian residuals, capturing spatial correlations that guide residual updates. In the temporal domain, a structured gating mechanism, comprising hierarchical feature propagation (HFP) and Gumbel-Sigmoid sampling, converts hierarchical dynamic cues into sparse residual update decisions under differentiable optimization. A multi-level discrete scheme is further adopted to provide fine-grained control over residual updates while preserving intricate dynamic details. Extensive experiments across consumer GPUs, industrial edge IoT devices, and a physical telepresence testbed demonstrate that S$^2$GS consistently reduces per-frame optimization time and storage footprint while maintaining competitive visual quality. Compared with QUEEN, S$^2$GS reduces per-frame optimization time by 59% and storage costs by 85% on an RTX 4090 GPU. On the Jetson AGX Orin, S$^2$GS delivers the highest rendering throughput (60+ FPS) and the lowest energy consumption among the evaluated methods, demonstrating its potential for deployment in resource-constrained systems.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.19639 — 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 2026-10-18T12:01:57.703Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).