Paper Detail

K2V: Generative Keyframing For Physically Plausible Video Generation

Felix O'Mahony, Daniel Olmeda Reino, Roberto Cipolla, Ayush Tewari

arxiv Score 12.8

Published 2026-11-12 · First seen 2026-11-13

General AI

Abstract

Video diffusion models are able to generate samples with high-quality appearance and textural qualities. However, content produced by these methods is known to exhibit significant physical errors. This is because, in a classical video generation setting, all physical reasoning must take place simultaneously and exclusively within the diffusion process.We propose to resolve these issues by redistributing the task of physical reasoning onto a language model-backed keyframe generation module, which allows for explicit reasoning in language, and fine-grained control over the appearance of the video at important moments in the video. We then condition a video generation model with these keyframes, reducing the role of the diffusion model to the simpler task of interpolating between physically-correct intermediate states, rather than inferring an entire sequence with diffusion. Results demonstrate that our approach significantly outperforms existing approaches, achieving state-of-the-art performance on the Physics-IQ Verified benchmark and PhyGenBench.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{omahony2026k2v,
  title = {K2V: Generative Keyframing For Physically Plausible Video Generation},
  author = {Felix O'Mahony and Daniel Olmeda Reino and Roberto Cipolla and Ayush Tewari},
  year = {2026},
  abstract = {Video diffusion models are able to generate samples with high-quality appearance and textural qualities. However, content produced by these methods is known to exhibit significant physical errors. This is because, in a classical video generation setting, all physical reasoning must take place simultaneously and exclusively within the diffusion process.We propose to resolve these issues by redistributing the task of physical reasoning onto a language model-backed keyframe generation module, which},
  url = {https://arxiv.org/abs/2611.17324},
  keywords = {cs.CV},
  eprint = {2611.17324},
  archiveprefix = {arXiv},
}

Metadata

{}