Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces Unified Motion Flow (UMF), a flow-matching based approach for number-free text-to-motion generation that handles variable numbers of agents. UMF uses a unified latent space to train on heterogeneous motion datasets and decomposes motion generation into a single-pass prior generation (Pyramid Motion Flow) and multi-pass reaction generation (Semi-Noise Motion Flow). Experiments demonstrate UMF's effectiveness as a generalist model for multi-person motion generation from text, addressing limitations of autoregressive methods.
Forget brittle, recursive motion generation: UMF's flow-matching approach unlocks efficient, number-free text-to-motion synthesis across diverse datasets.
Generative models excel at motion synthesis for a fixed number of agents but struggle to generalize with variable agents. Based on limited, domain-specific data, existing methods employ autoregressive models to generate motion recursively, which suffer from inefficiency and error accumulation. We propose Unified Motion Flow (UMF), which consists of Pyramid Motion Flow (P-Flow) and Semi-Noise Motion Flow (S-Flow). UMF decomposes the number-free motion generation into a single-pass motion prior generation stage and multi-pass reaction generation stages. Specifically, UMF utilizes a unified latent space to bridge the distribution gap between heterogeneous motion datasets, enabling effective unified training. For motion prior generation, P-Flow operates on hierarchical resolutions conditioned on different noise levels, thereby mitigating computational overheads. For reaction generation, S-Flow learns a joint probabilistic path that adaptively performs reaction transformation and context reconstruction, alleviating error accumulation. Extensive results and user studies demonstrate UMF's effectiveness as a generalist model for multi-person motion generation from text. Project page: https://githubhgh.github.io/umf/.