Metraipolis › archive › dc_3206649b1e21

Gen2-VC: Unlocking Generative Priors for Video Compression — arXiv:2609.34725

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.34725
License (as archived): CC0-1.0
Archived: 2026-10-08T01:37:23.032Z
SHA-256 of the archived text: bc1069ddcc17ebf669ece50712d1c83977252d2984f9026c50e1f5ac9cdf5ad2
Stable URL of this page: https://metraipolis.com/documento/dc_3206649b1e21

How to cite

Gen2-VC: Unlocking Generative Priors for Video Compression — arXiv:2609.34725 — arXiv (en), https://arxiv.org/abs/2609.34725 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3206649b1e21 (Metraipolis archive dc_3206649b1e21, sha256 bc1069ddcc17ebf669ece50712d1c83977252d2984f9026c50e1f5ac9cdf5ad2)

BibTeX

@misc{dc3206649b1e21,
  title = {Gen2-VC: Unlocking Generative Priors for Video Compression — arXiv:2609.34725},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34725},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3206649b1e21; sha256 bc1069ddcc17ebf669ece50712d1c83977252d2984f9026c50e1f5ac9cdf5ad2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34725. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Under stringent bitrate constraints, existing video codecs struggle to balance source fidelity and perceptual realism. Distortion-oriented codecs often oversmooth details, while generative codecs risk introducing content and structural deviations and rely on codec-specific designs. This motivates a question: Can existing codecs achieve a better distortion--perception trade-off through simple, reusable adaptation? Our insight is that native codec reconstructions provide a shared interface through which generative refinement is anchored to source content while remaining decoupled from codec-specific representations. We therefore propose Gen2-VC, a generative video compression framework that enhances the outputs of learned and conventional codecs with a pretrained video prior, leaving their bitstreams and reference update processes unchanged. With the codec, VAE, and generative backbone frozen, lightweight LoRA adapters refine codec reconstruction through single-frame spatial adaptation followed by multi-frame temporal adaptation with the video prior. Using Wan2.1-T2V-1.3B, Gen2-VC-DCVC-UF outperforms previous leading codecs in LPIPS/DISTS and, to our knowledge, is the first generative video codec to surpass VTM-23.0 in both PSNR and MS-SSIM at low bitrates, based on BD-rates averaged over six datasets. Compared to VTM-23.0, it reduces bitrate by an average of 86.65% and 94.24% at matched LPIPS and DISTS, respectively. Adapters trained only on DCVC-UF improve perceptual quality on DCVC-RT, ECM, VTM, and HM without retraining.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in eess.IV).
Categorie arXiv: Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2609.34725 — 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 2026-10-08T01:11:39.819Z dalla pagina https://arxiv.org/catchup/eess.IV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).