Metraipolis › archive › dc_a652eed47c2d

ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation — arXiv:2608.30184

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30184
License (as archived)
CC0-1.0
Archived
2026-10-17T09:59:21.861Z
SHA-256 of the archived text
ef7c4db96adb42719182ff213ceb745babd518c0506a9333c76d3c6394fe31e5
Stable URL of this page
https://metraipolis.com/documento/dc_a652eed47c2d

How to cite

ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation — arXiv:2608.30184 — arXiv (en), https://arxiv.org/abs/2608.30184 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a652eed47c2d (Metraipolis archive dc_a652eed47c2d, sha256 ef7c4db96adb42719182ff213ceb745babd518c0506a9333c76d3c6394fe31e5)
BibTeX
@misc{dca652eed47c2d,
  title = {ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation — arXiv:2608.30184},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30184},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a652eed47c2d; sha256 ef7c4db96adb42719182ff213ceb745babd518c0506a9333c76d3c6394fe31e5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30184. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Volumetric video enables immersive free viewpoint rendering of dynamic real world scenes, yet existing methods struggle with long sequences and complex motions, often leading to temporal instability and visual artifacts. To address these challenges, we propose \ourname, a Gaussian splatting based framework for volumetric video reconstruction. Our key insight is that explicitly tracking long term complex motion with individual Gaussian primitives is inherently unstable. Instead, we organize Gaussians around time conditioned anchors that localize their spatial and temporal support, thereby reducing long range motion complexity. We further introduce a temporal windowing strategy to activate only anchors relevant to the queried time, which improves scalability and temporal coherence. In addition, to ensure spatial and temporal stability, we design a compact set of multi level anchor features that encode global features, local spatial features, and local temporal features, jointly constraining Gaussian generation. Extensive experiments demonstrate that \ourname \ consistently outperforms prior methods on long sequence volumetric videos with complex motions. Project page: this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.30184 — 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 2026-10-17T09:28:48.117Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).