English

Length-Aware Motion Synthesis via Latent Diffusion

Computer Vision and Pattern Recognition 2024-07-17 v1

Abstract

The target duration of a synthesized human motion is a critical attribute that requires modeling control over the motion dynamics and style. Speeding up an action performance is not merely fast-forwarding it. However, state-of-the-art techniques for human behavior synthesis have limited control over the target sequence length. We introduce the problem of generating length-aware 3D human motion sequences from textual descriptors, and we propose a novel model to synthesize motions of variable target lengths, which we dub "Length-Aware Latent Diffusion" (LADiff). LADiff consists of two new modules: 1) a length-aware variational auto-encoder to learn motion representations with length-dependent latent codes; 2) a length-conforming latent diffusion model to generate motions with a richness of details that increases with the required target sequence length. LADiff significantly improves over the state-of-the-art across most of the existing motion synthesis metrics on the two established benchmarks of HumanML3D and KIT-ML.

Keywords

Cite

@article{arxiv.2407.11532,
  title  = {Length-Aware Motion Synthesis via Latent Diffusion},
  author = {Alessio Sampieri and Alessio Palma and Indro Spinelli and Fabio Galasso},
  journal= {arXiv preprint arXiv:2407.11532},
  year   = {2024}
}

Comments

Accepted at ECCV 2024

R2 v1 2026-06-28T17:42:45.345Z