Metraipolis › archive › dc_7ccbddc820f7
Information Capacity of Generative Video Compression: Quantifying the Rate-Compute Exchange at Identical Quality — arXiv:2609.27493
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27493
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:34:53.542Z
- SHA-256 of the archived text
5c4bc84ec5ac3aaa843d7921cba9e5e3b26e3984d2a479f6fb514956bb60d95f- Stable URL of this page
https://metraipolis.com/documento/dc_7ccbddc820f7
How to cite
Information Capacity of Generative Video Compression: Quantifying the Rate-Compute Exchange at Identical Quality — arXiv:2609.27493 — arXiv (en), https://arxiv.org/abs/2609.27493 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ccbddc820f7 (Metraipolis archive dc_7ccbddc820f7, sha256 5c4bc84ec5ac3aaa843d7921cba9e5e3b26e3984d2a479f6fb514956bb60d95f)
BibTeX
@misc{dc7ccbddc820f7,
title = {Information Capacity of Generative Video Compression: Quantifying the Rate-Compute Exchange at Identical Quality — arXiv:2609.27493},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27493},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ccbddc820f7; sha256 5c4bc84ec5ac3aaa843d7921cba9e5e3b26e3984d2a479f6fb514956bb60d95f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27493. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Under the AI Flow framework, communication networks distribute intelligence across devices, edge servers, and clouds, and computation at the receiver becomes a resource that can substitute for transmitted bits. Generative video compression (GVC) embodies this exchange by sending compact tokens with ultra-low bitrate and letting a generative decoder synthesize the video, yet how much bandwidth savings a unit of decoder compute actually achieves has never been quantified. To fill this vacancy, we model reconstruction quality as a two-factor power law in data rate and decoder compute, which fits measured DISTS of two GVC decoders with a mean error below 3%, and define the information capacity (IC) as the negative logarithmic slope along an iso-quality contour, namely the fraction of rate saved per fractional increase in compute at identical quality. IC is dimensionless and unit-invariant, thus enabling an architecture-agnostic comparison. It forms a field over the operating plane, locating where additional denoising steps are worth their cost. Across five datasets, the 14B decoder trades more compute for fewer rate about ten times more efficiently than the 1.3B decoder. IC also varies significantly across datasets, indicating imbalanced performance on the rate-compute trade-off in GVC methods. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.27493 — 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 2026-10-08T12:12:35.689Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).