Reimagine Video Dynamics
Its authors withdrew this paper, so there is no full text to read or summarize.
Lists
Only you see this
Abstract
Most video editing methods focus on changing the appearance of the source video, while offering limited control over its dynamics. We introduce Reimagine Video Dynamics (RVD), a framework that disentangles a compact, editable dynamics token from visual context. We learn this token through self-supervised reconstruction: given the first frame as visual context, a renderer must recover the original video from the dynamics token, encouraging it to capture how the scene evolves rather than how it looks. This disentanglement allows video dynamics to be edited directly while preserving visual context. We develop a language-guided dynamics-token editor that transforms source dynamics into target dynamics, and train it with a scalable counterfactual video-pair pipeline and a two-stage training strategy. Extensive experiments show that RVD enables effective video dynamics editing, training-free retiming, and appearance-controlled re-rendering.
BibTeX
@misc{yuan2027reimagine,
author = {Yu Yuan and Yawen Lu and Guoxian Song and Kevin Duarte and Ratheesh Kalarot and Di Chang and Xijun Wang and Stanley H. Chan},
title = {{Reimagine Video Dynamics}},
year = {2027},
url = {https://openreview.net/forum?id=JCUo80Q8Py},
howpublished = {OpenReview},
note = {Submitted to ICLR 2027},
}Loading related content...