Unified Number-Free Text-to-Motion Generation Via Flow Matching

• URL: http://arxiv.org/abs/2603.27040v1
• Date: Fri, 27 Mar 2026 23:10:56 GMT
• Title: Unified Number-Free Text-to-Motion Generation Via Flow Matching
• Abstract summary: Generative models excel at motion synthesis for a fixed number of agents but struggle to generalize with variable agents.<n>We propose Unified Motion Flow (UMF), which consists of Pyramid Motion Flow (P-Flow) and Semi-Noise Motion Flow (S-Flow)<n>UMF decomposes the number-free motion generation into a single-pass motion prior generation stage and multi-pass reaction generation stages.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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/.

Related papers

• MotionHiFlow: Text-to-motion via hierarchical flow matching [23.3063383764363]
  Text-to-motion generation aims to generate 3D human motions that are tightly aligned with the input text.<n>We propose textitMotionHiFlow, a hierarchical flow matching framework to generate motion progressively.<n>The flows at lower scales capture high-level semantics and coarse motion structures, while flows at higher scales refine temporal details.
  arXiv  Detail & Related papers  (2026-04-25T12:16:37Z)
• Riemannian MeanFlow for One-Step Generation on Manifolds [54.09734511705173]
  Flow Matching enables simulation-free training of generative models.<n>MeanFlow can be extended to manifold-valued generation where velocities lie in location-dependent tangent spaces.<n>Experiments on spheres, tori, and SO(3) demonstrate competitive one-step sampling with improved quality-efficiency trade-offs and substantially reduced sampling cost.
  arXiv  Detail & Related papers  (2026-03-11T12:41:46Z)
• Trajectory Stitching for Solving Inverse Problems with Flow-Based Models [68.36374645801901]
  Flow-based generative models have emerged as powerful priors for solving inverse problems.<n>We propose MS-Flow, which represents the trajectory as a sequence of intermediate latent states rather than a single initial code.<n>We demonstrate the effectiveness of MS-Flow over existing methods on image recovery and inverse problems, including inpainting, super-resolution, and computed tomography.
  arXiv  Detail & Related papers  (2026-02-09T11:36:41Z)
• Unified Multi-Modal Interactive & Reactive 3D Motion Generation via Rectified Flow [17.95248351806955]
  We introduce DualFlow, a framework for multi-modal two-person motion generation.<n>It synthesises motion on diverse inputs, including text, music, and prior motion sequences.<n>It produces temporally coherent and rhythmically synchronized motions, setting state-of-the-art in multi-modal human motion generation.
  arXiv  Detail & Related papers  (2025-09-28T22:36:18Z)
• MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing [53.98607267063729]
  MotionVerse is a framework to comprehend, generate, and edit human motion in both single-person and multi-person scenarios.<n>We employ a motion tokenizer with residual quantization, which converts continuous motion sequences into multi-stream discrete tokens.<n>We also introduce a textitDelay Parallel Modeling strategy, which temporally staggers the encoding of residual token streams.
  arXiv  Detail & Related papers  (2025-09-28T04:20:56Z)
• ARFlow: Human Action-Reaction Flow Matching with Physical Guidance [36.052383171690614]
  Action-Reaction Flow Matching (ARFlow) is a novel framework that establishes direct action-to-reaction mappings.<n>Our approach introduces a physical guidance mechanism specifically designed for Flow Matching (FM) that effectively prevents body penetration artifacts during sampling.
  arXiv  Detail & Related papers  (2025-03-21T09:41:24Z)
• ActionFlow: Equivariant, Accurate, and Efficient Policies with Spatially Symmetric Flow Matching [20.20511152176522]
  ActionFlow is a policy class that integrates spatial symmetry inductive biases. On the representation level, ActionFlow introduces an SE(3) Invariant Transformer architecture. For action generation, ActionFlow leverages Flow Matching, a state-of-the-art deep generative model.
  arXiv  Detail & Related papers  (2024-09-06T19:30:36Z)
• Efficient Text-driven Motion Generation via Latent Consistency Training [21.348658259929053]
  We propose a motion latent consistency training framework (MLCT) to solve nonlinear reverse diffusion trajectories.<n>By combining these enhancements, we achieve stable and consistency training in non-pixel modality and latent representation spaces.
  arXiv  Detail & Related papers  (2024-05-05T02:11:57Z)
• Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows [53.31856123113228]
  This paper proposes Language Rectified Flow (ours) Our method is based on the reformulation of the standard probabilistic flow models. Experiments and ablation studies demonstrate that our method can be general, effective, and beneficial for many NLP tasks.
  arXiv  Detail & Related papers  (2024-03-25T17:58:22Z)
• Motion Flow Matching for Human Motion Synthesis and Editing [75.13665467944314]
  We propose emphMotion Flow Matching, a novel generative model for human motion generation featuring efficient sampling and effectiveness in motion editing applications. Our method reduces the sampling complexity from thousand steps in previous diffusion models to just ten steps, while achieving comparable performance in text-to-motion and action-to-motion generation benchmarks.
  arXiv  Detail & Related papers  (2023-12-14T12:57:35Z)
• Guided Flows for Generative Modeling and Decision Making [55.42634941614435]
  We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text synthesis-to-speech. Notably, we are first to apply flow models for plan generation in the offline reinforcement learning setting ax speedup in compared to diffusion models.
  arXiv  Detail & Related papers  (2023-11-22T15:07:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.