titleMPEG-Diffusion: Mixed-Resolution Video Generation
authorsDennis Menn, Tianpei Gu, Guande He, Aryan V S, Yanke Song, Nan Liu, Desai Xie, Xun Huang, Chenfeng Xu, Diana Marculescu
date2026-11-09
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.12069
affiliationRoblox Corporation
upvotes8 (Hugging Face Daily Papers, 2026-11-19)
linksabs pdf hf
cite
abstractVideo diffusion transformers (DiTs) generate realistic videos, but their heavy computational cost limits broader real-world applications. Mixed-resolution generation reduces this cost by generating the visually important region at high resolution (HR) and the rest at low resolution (LR), yet existing methods suffer a severe quality drop on videos and require knowing the HR region in advance. We show that these failures are not inherent to mixed resolution, and propose MPEG-Diffusion to address their three root causes: (1) dual-resolution attention to mitigate the curse of mixed resolution, where each query reads the K/V of its own resolution, (2) a mixed-resolution decoder to blend the HR and LR latents before decoding and resolve distortion, and (3) a self-selected HR region using the DiT's knowledge to find the visually important region without requiring it in advance. Processing only 30% of full-resolution tokens, MPEG-Diffusion speeds up denoising by 4.8times on Wan2.1 14B (3.8times on 1.3B), outperforming prior methods on nearly every metric. In the user study, we demonstrate the high quality of MPEG-Diffusion, with raters preferring it over prior mixed-resolution methods in over 90% of pairs and rating it close to full resolution.

bibtex

@misc{menn2026mpeg,
  title={MPEG-Diffusion: Mixed-Resolution Video Generation},
  author={Dennis Menn and Tianpei Gu and Guande He and Aryan V S and Yanke Song and Nan Liu and Desai Xie and Xun Huang and Chenfeng Xu and Diana Marculescu},
  year={2026},
  eprint={2611.12069},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2611.12069}
}