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

Guanhe Huang; Oya Celiktutan

cs.CVMar 27, 2026

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

Authors: Guanhe Huang, Oya Celiktutan

Organizations: King’s College London

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/.

Figures & tables

Figure 1: Core contribution of UMF. We show dual-agent cases here for simplicity. (a) Standard methods [ 51 , 55 ] are restricted to a fixed number of agents. (b) Autoregressive methods [ 12 ] decouple generation into a motion prior and subsequent reaction. The reaction is typically guided by the prior using a conditioning network. (c) Our UMF leverages a heterogeneous motion prior as the adaptive start point of the reaction flow path, mitigating error accumulation.

Figure 2: Overview of the Unified Motion Flow (UMF) architecture. The UMF framework consists of three stages. (A) Unified motion VAE: A motion VAE with latent adapters encodes raw motions from heterogeneous datasets (e.g., HumanML3D [ 14 ] , InterHuman [ 32 ] ) into a regularized multi-token latent representation ( $Z$ ). (B) P-Flow motion prior generation: The Pyramid Flow Transformer synthesizes the latent motion prior ( $\check{Z}$ ) based on noisy latent motion and text conditions. The P-Flow operates hierarchically based on the timestep $t\sim(0,1)$ : it processes downsampled, low-resolution latents for $t<p$ and switches to original-resolution latents for $t>p$ , mitigating multi-token computational overheads. (C) S-Flow reaction generation: Based on the previously generated latent { $\check{Z}_{i},\dots,\check{Z}_{1}$ }, the context adapter generates the context motion $C$ . Then the Semi-Noise Flow transformer predicts the reaction latent ( $\check{W}$ ) by jointly modeling context reconstruction and reaction transformation, alleviating the error accumulation from previously generated motion.

Panel of Figure 3 — Figure 3: Qualitative comparison (zoom into see it better) between FreeMotion [ 12 ] and UMF. Red circles demonstrate successful cases, while Blue circles show failure cases.

Method	R Top 1 $\uparrow$	R Top 2 $\uparrow$	R Top 3 $\uparrow$	FID $\downarrow$	MM Dist $\downarrow$	Diversity $\rightarrow$	MModality $\uparrow$
Ground Truth	$0.452^{\pm 0.008}$	$0.610^{\pm 0.009}$	$0.701^{\pm 0.008}$	$0.273^{\pm 0.007}$	$3.755^{\pm 0.008}$	$7.948^{\pm 0.064}$	-
TEMOS [ 41 ]	$0.224^{\pm 0.010}$	$0.316^{\pm 0.013}$	$0.450^{\pm 0.018}$	$17.375^{\pm 0.043}$	$6.342^{\pm 0.015}$	$6.939^{\pm 0.071}$	$0.535^{\pm 0.014}$
T2M [ 14 ]	$0.238^{\pm 0.012}$	$0.325^{\pm 0.010}$	$0.464^{\pm 0.014}$	$13.769^{\pm 0.072}$	$5.731^{\pm 0.013}$	$7.046^{\pm 0.022}$	$1.387^{\pm 0.076}$
MDM [ 51 ]	$0.153^{\pm 0.012}$	$0.260^{\pm 0.009}$	$0.339^{\pm 0.012}$	$9.167^{\pm 0.056}$	$7.125^{\pm 0.018}$	$7.602^{\pm 0.045}$	$\mathbf{2.350^{\pm 0.080}}$
ComMDM [ 46 ]	$0.223^{\pm 0.009}$	$0.334^{\pm 0.008}$	$0.466^{\pm 0.010}$	$7.069^{\pm 0.054}$	$6.212^{\pm 0.021}$	$7.244^{\pm 0.038}$	$1.822^{\pm 0.052}$
InterGen [ 32 ]	$0.371^{\pm 0.010}$	$0.515^{\pm 0.012}$	$0.624^{\pm 0.010}$	$5.918^{\pm 0.079}$	$5.108^{\pm 0.014}$	$7.387^{\pm 0.029}$	$2.141^{\pm 0.063}$

Table 1: Quantitative evaluation on the InterHuman test sets.

\pm

indicates a 95% confidence interval and

\rightarrow

means the closer to ground truth the better. Boldface indicates the best result, while underline refers to the second best.

Methods	RTop3 $\uparrow$	FID $\downarrow$	MM Dist $\downarrow$	Diversity $\rightarrow$	MModality $\uparrow$
Real	$0.722^{\pm 0.004}$	$0.002^{\pm 0.0002}$	$3.503^{\pm 0.011}$	$5.390^{\pm 0.058}$	-
T2M [ 14 ]	$0.224^{\pm 0.003}$	$32.482^{\pm 0.098}$	$7.299^{\pm 0.016}$	$4.350^{\pm 0.073}$	$0.719^{\pm 0.041}$
MDM [ 51 ]	$0.370^{\pm 0.006}$	$3.397^{\pm 0.052}$	$8.640^{\pm 0.045}$	$4.780^{\pm 0.015}$	$2.288^{\pm 0.039}$
MDM-GRU [ 51 ]	$0.328^{\pm 0.012}$	$6.397^{\pm 0.214}$	$8.884^{\pm 0.040}$	$4.851^{\pm 0.081}$	$2.076^{\pm 0.040}$
RAIG [ 49 ]	$0.363^{\pm 0.008}$	$2.915^{\pm 0.029}$	$7.294^{\pm 0.027}$	$4.736^{\pm 0.099}$	$2.203^{\pm 0.049}$
InterGen [ 32 ]	$0.374^{\pm 0.005}$	$13.237^{\pm 0.035}$	$10.929^{\pm 0.026}$	$4.376^{\pm 0.042}$	$\mathbf{2.793^{\pm 0.014}}$

Table 2: Comparison to state-of-the-art for human action-reaction synthesis on the InterHuman-AS dataset.

\pm

indicates 95% confidence interval,

\rightarrow

means that closer to Real is better. Bold indicates best result and underline indicates second best.

	Components			HumanML3D		InterHuman
Method	HP	LA	MT	RTop3 $\uparrow$	FID $\downarrow$	RTop3 $\uparrow$	FID $\downarrow$
Real Data	-	-	-	0.797	0.002	0.701	0.273
FreeMotion	✓	-	-	0.612	3.539	0.503	7.984
w/o HP	✗	-	-	0.128	13.155	0.544	6.740
UMF (Full)	✓	✓	✓	0.729	0.486	0.694	4.772
w/o HP	✗	✓	✓	0.134	10.806	0.651	4.933

Table 3: Ablation study of individual priors on the HumanML3D and InterHuman datasets. HP : H eterogeneous P riors; LA : L atent A dapter; MT : M ulti-token T okenizer.

Methods	$T_{P_{2}}$	$T_{P_{1}}$	$T_{S}$	FID $\downarrow$	RTop3 $\uparrow$	FLOPs(G) $\downarrow$	AITS $\downarrow$
FreeMotion	-	-	-	6.740	0.544	217.8	3.059
UMF	45	5	10	4.772	0.694	140.3	0.623
UMF-PFK1	-	50	10	4.761	0.674	320.2	1.119
UMF-PFS	45	5	10	7.238	0.527	135.9	0.581
UMF-Fast	5	5	10	4.937	0.687	74.7	0.439
UMF-Symmetric	25	25	10	4.784	0.697	206.0	0.874

Table 4: Ablation study of Pyramid Flow on the InterHuman dataset. UMF has a 2-stage temporal pyramid structure. We report FLOPs(G) and AITS (Average Inference Time in Seconds).

T_{P2}

T_{P1}

, and

T_{S}

refer to the corresponding inference step for P-Flow low-res stage, P-Flow full-res stage, and S-Flow, respectively. UMF-PFK1 and UMF-PFS refer to P-Flow with the original resolution and with the spatial pyramid structure, respectively.

Methods	FID $\downarrow$	RTop3 $\uparrow$	Diversity $\rightarrow$
UMF	4.772	0.694	8.039
UMF w. Shared Transformer	6.206	0.644	8.088
UMF w. Noise-Free path [ 27 ]	5.617	0.646	8.112
UMF w. ControlNet [ 66 ]	6.868	0.637	8.061
UMF w/o. Context Adapter	7.038	0.642	8.087
UMF w/o. $L_{recons}$	5.765	0.649	8.124

Table 5: Ablation study of Semi-Noise Flow on the InterHuman dataset.

Figure 4: The UMF number-free zero-shot generation user study. We asked users to compare our UMF ( Blue Bar ) to the FreeMotion ( Red Bar ) in a side-by-side view. The dashed line marks 50%. UMF outperforms FreeMotion in all three aspects of generation.

Explore similar work

FlowCoMotion: Text-to-Motion Generation via Token-Latent Flow Modeling
Apr 13, 2026Dawei Guan, Di Yang, Chengjie Jin +1Text-to-Motion Generation Human Motion Generation
School of Artificial Intelligence and Data Science, University of Science and Technology of China · Suzhou Institute for Advanced Research, University of Science and Technology of China
OpenT2M: No-frill Motion Generation with Open-source,Large-scale, High-quality Data
Mar 19, 2026Bin Cao, Sipeng Zheng, Hao Luo +3Text-to-Motion Generation Human Motion Generation
CASIA · UCAS · BAAI +3
MotionMaestro: Masked Tokenization for Unified Motion Generation
Sep 26, 2026Yun Chen, Munchurl Kim, Jeonghyeok DoHuman Motion Generation Conditional Generative Modeling
Korea Advanced Institute of Science and Technology (KAIST)

Apr 13, 2026J/K move · Enter open · S save

FlowCoMotion: Text-to-Motion Generation via Token-Latent Flow Modeling

Dawei Guan, Di Yang, Chengjie Jin, Jiangtao Wang

School of Artificial Intelligence and Data Science, University of Science and Technology of China · Suzhou Institute for Advanced Research, University of Science and Technology of China

Text-to-Motion Generation Human Motion Generation Motion Representation Learning Flow-Based Generative Modeling

Open paper AskPDF arXiv

Text-to-motion generation is driven by learning motion representations for semantic alignment with language. Existing methods rely on either continuous or discrete motion representations. However, continuous representations entangle semantics with dynamics, while discrete representations lose fine-grained motion details. In this context, we propose FlowCoMotion, a novel motion generation framework that unifies both treatments from a modeling perspective. Specifically, FlowCoMotion employs token-latent coupling to capture both semantic content and high-fidelity motion details. In the latent branch, we apply multi-view distillation to regularize the continuous latent space, while in the token branch we use discrete temporal resolution quantization to extract high-level semantic cues. The motion latent is then obtained by combining the representations from the two branches through a token-latent coupling network. Subsequently, a velocity field is predicted based on the textual conditions. An ODE solver integrates this velocity field from a simple prior, thereby guiding the sample to the potential state of the target motion. Extensive experiments show that FlowCoMotion achieves competitive performance on text-to-motion benchmarks, including HumanML3D and SnapMoGen.

Abstract

Explore similar work

FlowCoMotion: Text-to-Motion Generation via Token-Latent Flow Modeling

OpenT2M: No-frill Motion Generation with Open-source,Large-scale, High-quality Data

MotionMaestro: Masked Tokenization for Unified Motion Generation