Metraipolis › archive › dc_158e7934ffb5

RIFT: Residual-Informed Flow Transfer for One-Step Generative Video Compression — arXiv:2611.01791

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01791
License (as archived)
CC0-1.0
Archived
2026-11-03T11:41:40.538Z
SHA-256 of the archived text
d7120ed93240ed85604222fc09d05c2fac0dd5263b87e18c6f509317a1e8cba7
Stable URL of this page
https://metraipolis.com/documento/dc_158e7934ffb5

How to cite

RIFT: Residual-Informed Flow Transfer for One-Step Generative Video Compression — arXiv:2611.01791 — arXiv (en), https://arxiv.org/abs/2611.01791 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_158e7934ffb5 (Metraipolis archive dc_158e7934ffb5, sha256 d7120ed93240ed85604222fc09d05c2fac0dd5263b87e18c6f509317a1e8cba7)
BibTeX
@misc{dc158e7934ffb5,
  title = {RIFT: Residual-Informed Flow Transfer for One-Step Generative Video Compression — arXiv:2611.01791},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01791},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_158e7934ffb5; sha256 d7120ed93240ed85604222fc09d05c2fac0dd5263b87e18c6f509317a1e8cba7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01791. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in video generation have enabled generative video compression to reconstruct details lost during coding using pretrained spatiotemporal priors. However, a substantial gap remains between codec-induced degradation and the perturbation trajectories learned by flow-matching models. In this paper, we identify a compression-dependent directional mismatch that degradation-strength-based timestep calibration alone cannot resolve. Compressed latents remain strongly aligned across codec operating points, while their reconstruction residuals vary substantially in magnitude and direction. To bridge this gap, we propose RIFT, a Residual-Informed Flow Transfer framework for one-step generative video compression. At its core, RIFT introduces a Residual Geometry Inducer (RGI) that converts the pretrained flow prediction into a content-adaptive restoration update using decoder-visible codec cues. RGI integrates flow-timestep conditioning with a learned full-band residual-strength estimate and content-conditioned direction and gain modulation, aligning the orientation and magnitude of the update with the compression-dependent residual geometry. Extensive experiments on three public video compression benchmarks show that RIFT outperforms competing generative video compression methods. The code is publicly available on RIFT.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.01791 — 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 2026-11-03T11:06:37.513Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).