Metraipolis › archive › dc_bd387fce58ff

GVC-RT: Towards Real-Time Generative Video Compression at Ultra-Low Bitrates — arXiv:2608.04891

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.04891
License (as archived): CC0-1.0
Archived: 2026-10-31T12:13:29.394Z
SHA-256 of the archived text: 5b12345f9fdaf80123456425cabeca676c52bf1b3d47b6265cceb7c1c1ea88bc
Stable URL of this page: https://metraipolis.com/documento/dc_bd387fce58ff

How to cite

GVC-RT: Towards Real-Time Generative Video Compression at Ultra-Low Bitrates — arXiv:2608.04891 — arXiv (en), https://arxiv.org/abs/2608.04891 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd387fce58ff (Metraipolis archive dc_bd387fce58ff, sha256 5b12345f9fdaf80123456425cabeca676c52bf1b3d47b6265cceb7c1c1ea88bc)

BibTeX

@misc{dcbd387fce58ff,
  title = {GVC-RT: Towards Real-Time Generative Video Compression at Ultra-Low Bitrates — arXiv:2608.04891},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04891},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd387fce58ff; sha256 5b12345f9fdaf80123456425cabeca676c52bf1b3d47b6265cceb7c1c1ea88bc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04891. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent generative video codecs (GVCs) have achieved impressive reconstruction fidelity at ultra-low bitrates (< 0.02 bits per pixel) by compressing the tokens from generative tokenizers. However, existing GVCs generally require considerable computation time and model complexity, which hinder their deployment on compute-limited devices and in real-time applications. To bridge this gap, we systematically identify the computational bottlenecks and propose GVC-RT, which redesigns the generative latent coding framework to realize real-time video coding without sacrificing compression performance. Specifically, built on a pretrained lookup-free quantization (LFQ) tokenizer, GVC-RT adopts an asymmetric architecture that directly learns to match the LFQ latent distribution, while generative-space alignment is enforced via a regularization loss term only during training. In this manner, we bypass heavy tokenization and entirely remove the complex feature-alignment process at inference time. Moreover, we further introduce a lightweight de-tokenizer architecture to resolve the final latency bottleneck during decoding. Experimental results demonstrate that GVC-RT outperforms the previous SOTA model, GLC-Video, with average BD-rate savings of 12.4% and 48.8% in terms of DISTS and LPIPS, while achieving encoding/decoding speeds of 123.1/55.1 fps for 1080p video. The code is at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in eess.SP).
Categorie arXiv: Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2608.04891 — 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 2026-10-31T12:03:54.946Z dalla pagina https://arxiv.org/catchup/eess.SP/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).