English

Motion-Conditioned Image Animation for Video Editing

Graphics 2023-12-01 v1 Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Multimedia

Abstract

We introduce MoCA, a Motion-Conditioned Image Animation approach for video editing. It leverages a simple decomposition of the video editing problem into image editing followed by motion-conditioned image animation. Furthermore, given the lack of robust evaluation datasets for video editing, we introduce a new benchmark that measures edit capability across a wide variety of tasks, such as object replacement, background changes, style changes, and motion edits. We present a comprehensive human evaluation of the latest video editing methods along with MoCA, on our proposed benchmark. MoCA establishes a new state-of-the-art, demonstrating greater human preference win-rate, and outperforming notable recent approaches including Dreamix (63%), MasaCtrl (75%), and Tune-A-Video (72%), with especially significant improvements for motion edits.

Keywords

Cite

@article{arxiv.2311.18827,
  title  = {Motion-Conditioned Image Animation for Video Editing},
  author = {Wilson Yan and Andrew Brown and Pieter Abbeel and Rohit Girdhar and Samaneh Azadi},
  journal= {arXiv preprint arXiv:2311.18827},
  year   = {2023}
}

Comments

Project page: https://facebookresearch.github.io/MoCA

R2 v1 2026-06-28T13:37:26.960Z