English

How Animals Dance (When You're Not Looking)

Computer Vision and Pattern Recognition 2025-11-26 v2 Graphics

Abstract

We present a framework for generating music-synchronized, choreography aware animal dance videos. Our framework introduces choreography patterns -- structured sequences of motion beats that define the long-range structure of a dance -- as a novel high-level control signal for dance video generation. These patterns can be automatically estimated from human dance videos. Starting from a few keyframes representing distinct animal poses, generated via text-to-image prompting or GPT-4o, we formulate dance synthesis as a graph optimization problem that seeks the optimal keyframe structure to satisfy a specified choreography pattern of beats. We also introduce an approach for mirrored pose image generation, essential for capturing symmetry in dance. In-between frames are synthesized using an video diffusion model. With as few as six input keyframes, our method can produce up to 30 seconds dance videos across a wide range of animals and music tracks.

Keywords

Cite

@article{arxiv.2505.23738,
  title  = {How Animals Dance (When You're Not Looking)},
  author = {Xiaojuan Wang and Aleksander Holynski and Brian Curless and Ira Kemelmacher and Steve Seitz},
  journal= {arXiv preprint arXiv:2505.23738},
  year   = {2025}
}

Comments

Project page: https://how-animals-dance.github.io/

R2 v1 2026-07-01T02:48:56.694Z