Metraipolis › archive › dc_56e19e24d79e
FastVR: Efficient Streaming Video Restoration with One-Step Diffusion — arXiv:2609.36757
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36757
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:38:24.706Z
- SHA-256 of the archived text
b476c6fe28a0f9a0dfa7276c780eb083e897add0ff15c973e6f35dbc8069308b- Stable URL of this page
https://metraipolis.com/documento/dc_56e19e24d79e
How to cite
FastVR: Efficient Streaming Video Restoration with One-Step Diffusion — arXiv:2609.36757 — arXiv (en), https://arxiv.org/abs/2609.36757 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_56e19e24d79e (Metraipolis archive dc_56e19e24d79e, sha256 b476c6fe28a0f9a0dfa7276c780eb083e897add0ff15c973e6f35dbc8069308b)
BibTeX
@misc{dc56e19e24d79e,
title = {FastVR: Efficient Streaming Video Restoration with One-Step Diffusion — arXiv:2609.36757},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36757},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_56e19e24d79e; sha256 b476c6fe28a0f9a0dfa7276c780eb083e897add0ff15c973e6f35dbc8069308b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36757. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Diffusion-based video restoration recovers realistic details, but its practical deployment is limited by two efficiency bottlenecks: costly VAE encoding and decoding, and the quadratic cost of full self-attention in diffusion transformers (DiTs). This paper presents FastVR, a streaming video restoration framework built on a one-step diffusion model, which delivers strong restoration quality and temporal consistency while processing 1080p video at 11 FPS on a single H20 GPU. To improve inference efficiency, FastVR combines a lightweight VAE with chunk-wise causal attention, which substantially reduces the computational cost. During training, it further adopts velocity consistency regularization and continuous trajectory learning, which improve restoration quality. Extensive experiments show that FastVR is more efficient than the evaluated diffusion baselines while achieving state-of-the-art performance on synthetic and real-world benchmarks. We hope that this work supports further progress in the community. 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/2609.36757 — 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 2026-10-07T18:04:24.738Z 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).