English

A Two-part Transformer Network for Controllable Motion Synthesis

Graphics 2023-06-22 v2

Abstract

Although part-based motion synthesis networks have been investigated to reduce the complexity of modeling heterogeneous human motions, their computational cost remains prohibitive in interactive applications. To this end, we propose a novel two-part transformer network that aims to achieve high-quality, controllable motion synthesis results in real-time. Our network separates the skeleton into the upper and lower body parts, reducing the expensive cross-part fusion operations, and models the motions of each part separately through two streams of auto-regressive modules formed by multi-head attention layers. However, such a design might not sufficiently capture the correlations between the parts. We thus intentionally let the two parts share the features of the root joint and design a consistency loss to penalize the difference in the estimated root features and motions by these two auto-regressive modules, significantly improving the quality of synthesized motions. After training on our motion dataset, our network can synthesize a wide range of heterogeneous motions, like cartwheels and twists. Experimental and user study results demonstrate that our network is superior to state-of-the-art human motion synthesis networks in the quality of generated motions.

Keywords

Cite

@article{arxiv.2304.12571,
  title  = {A Two-part Transformer Network for Controllable Motion Synthesis},
  author = {Shuaiying Hou and Hongyu Tao and Hujun Bao and Weiwei Xu},
  journal= {arXiv preprint arXiv:2304.12571},
  year   = {2023}
}

Comments

16 pages, 26 figures

R2 v1 2026-06-28T10:16:43.218Z