Metraipolis › archive › dc_49fa87b13cd0
GVCCTurbo: Rate-Compute Quality Scheduling for Codebook Driven Generative Compression — arXiv:2608.03517
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03517
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:59:41.740Z
- SHA-256 of the archived text
716fc56b913714b7445d1b429ccb266e84023b665dc63a67460957d3ecfb3790- Stable URL of this page
https://metraipolis.com/documento/dc_49fa87b13cd0
How to cite
GVCCTurbo: Rate-Compute Quality Scheduling for Codebook Driven Generative Compression — arXiv:2608.03517 — arXiv (en), https://arxiv.org/abs/2608.03517 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49fa87b13cd0 (Metraipolis archive dc_49fa87b13cd0, sha256 716fc56b913714b7445d1b429ccb266e84023b665dc63a67460957d3ecfb3790)
BibTeX
@misc{dc49fa87b13cd0,
title = {GVCCTurbo: Rate-Compute Quality Scheduling for Codebook Driven Generative Compression — arXiv:2608.03517},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03517},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49fa87b13cd0; sha256 716fc56b913714b7445d1b429ccb266e84023b665dc63a67460957d3ecfb3790},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03517. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Codebook-driven generative compression uses a pretrained image or video generator as a zero-shot visual prior and transmits compact codebook indices to guide reconstruction at ultra-low bitrate. Current codecs tie each finite-rate correction to a fresh prior evaluation, so shortening the sampler also removes correction slots that carry target-dependent information. We propose GVCCTurbo, a BPP-driven scheduler that separates expensive prior refreshes from codebook corrections: after calibrating an atom-count operating point and skip-gap ratio once per protocol, it maps a target codebook-payload bitrate to a trajectory length and refresh period, making BPP a schedule input instead of a fixed consequence of sampler length. The same endpoint-prediction and finite-rate steering interface covers GVCC-style rectified-flow video and DDCM-style diffusion image compression, preserving zero-training deployment and compatibility with future distilled priors. Native 1080p curves position the complete zero-shot codec in the ultra-low-bitrate regime. In a controlled 720p Wan-GVCC study, the scheduler cuts prior evaluations from 20 to 9 for a $\sim\!44\%$ measured decoding-time reduction shared across the whole schedule family, at a small shared LPIPS cost on high-motion content; within that family, uniform refresh thinning (pure-skip) is a boundary point, and the BPP-aware interior point trades $2.9\%$ fewer codebook-payload bits for consistently higher PSNR at comparable LPIPS. These results support BPP-to-compute scheduling as a controllable extension of sampler-length tuning, without requiring the allocated point to dominate every boundary point. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.03517 — 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 2026-10-31T12:45:33.256Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).