English

Single Motion Diffusion

Computer Vision and Pattern Recognition 2023-06-14 v2 Artificial Intelligence Graphics

Abstract

Synthesizing realistic animations of humans, animals, and even imaginary creatures, has long been a goal for artists and computer graphics professionals. Compared to the imaging domain, which is rich with large available datasets, the number of data instances for the motion domain is limited, particularly for the animation of animals and exotic creatures (e.g., dragons), which have unique skeletons and motion patterns. In this work, we present a Single Motion Diffusion Model, dubbed SinMDM, a model designed to learn the internal motifs of a single motion sequence with arbitrary topology and synthesize motions of arbitrary length that are faithful to them. We harness the power of diffusion models and present a denoising network explicitly designed for the task of learning from a single input motion. SinMDM is designed to be a lightweight architecture, which avoids overfitting by using a shallow network with local attention layers that narrow the receptive field and encourage motion diversity. SinMDM can be applied in various contexts, including spatial and temporal in-betweening, motion expansion, style transfer, and crowd animation. Our results show that SinMDM outperforms existing methods both in quality and time-space efficiency. Moreover, while current approaches require additional training for different applications, our work facilitates these applications at inference time. Our code and trained models are available at https://sinmdm.github.io/SinMDM-page.

Keywords

Cite

@article{arxiv.2302.05905,
  title  = {Single Motion Diffusion},
  author = {Sigal Raab and Inbal Leibovitch and Guy Tevet and Moab Arar and Amit H. Bermano and Daniel Cohen-Or},
  journal= {arXiv preprint arXiv:2302.05905},
  year   = {2023}
}

Comments

Video: https://www.youtube.com/watch?v=zuWpVTgb_0U, Project page: https://sinmdm.github.io/SinMDM-page, Code: https://github.com/SinMDM/SinMDM

R2 v1 2026-06-28T08:38:03.227Z