Metraipolis › archive › dc_0a6a0fec6281

SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video — arXiv:2609.37969

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37969
License (as archived)
CC0-1.0
Archived
2026-10-07T18:41:37.295Z
SHA-256 of the archived text
ea1d1b34d49f89790eb01cbaad5ec23c539f2b88ca00fe8f4d1f5777936f1dd5
Stable URL of this page
https://metraipolis.com/documento/dc_0a6a0fec6281

How to cite

SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video — arXiv:2609.37969 — arXiv (en), https://arxiv.org/abs/2609.37969 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0a6a0fec6281 (Metraipolis archive dc_0a6a0fec6281, sha256 ea1d1b34d49f89790eb01cbaad5ec23c539f2b88ca00fe8f4d1f5777936f1dd5)
BibTeX
@misc{dc0a6a0fec6281,
  title = {SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video — arXiv:2609.37969},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37969},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0a6a0fec6281; sha256 ea1d1b34d49f89790eb01cbaad5ec23c539f2b88ca00fe8f4d1f5777936f1dd5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37969. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

High-resolution video generation is expensive, as its cost grows rapidly with the number of spatiotemporal tokens. A practical alternative first generates a lower-resolution video and then applies a refiner, but conventional multi-step refinement introduces a second sampling bottleneck. We present SoL-Refiner, a one-step video refiner that transforms low-resolution model outputs into 4K videos with a single denoising step. Our three-stage recipe combines high-resolution continual training, reinforcement learning (RL) post-training, and a final one-step distillation. We introduce Refiner-Bench, a video refinement benchmark constructed from the outputs of different video generators, and use a shared-input protocol to compare refiners at approximately 2K output resolution. At 2K, the one-step SoL-Refiner outperforms all external refiners on the VBench and UniPercept averages, while at $3840\!\times\!2176$ it improves both metrics over the three-step LTX-2.3 Refiner. With the complete acceleration stack, SoL-Refiner achieves an $8.91\times$ speedup in refinement latency over the same baseline in our 2K latency setting.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.37969 — 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 2026-10-07T18:04:24.924Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).