AI Paper Atlas

Research map / Video / Video generation

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

Guanhe Huang, Oya Celiktutan

CVPR 2026 · Video › Video generation · approach: Text-to-motion diffusion · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add HumanML3D heterogeneous single-person prior (ablation)UMF · HumanML3DFID: 10.806 -> 0.486Improved
add HumanML3D heterogeneous single-person prior (ablation)UMF · InterHumanFID: 4.933 -> 4.772Improved
add latent adapter (ablation)UMF · InterHumanFID: 5.473 -> 4.772Improved
use multi-token instead of single-token latent (ablation)UMF · InterHumanFID: 5.231 -> 4.772Improved
use pyramid (temporal) flow instead of full-resolution flow (ablation)P-Flow · InterHumanFLOPs (G): 320.2 -> 140.3Improved
use temporal pyramid instead of spatial pyramid (ablation)P-Flow · InterHumanFID: 7.238 -> 4.772Improved
allocate asymmetric P-Flow steps (45/5) instead of symmetric (25/25) (ablation)P-Flow · InterHumanFLOPs (G): 206.0 -> 140.3Improved
use separate P-Flow and S-Flow transformers instead of shared (ablation)UMF · InterHumanFID: 6.206 -> 4.772Improved
add context reconstruction path (semi-noise) over noise-free path (ablation)S-Flow · InterHumanFID: 5.617 -> 4.772Improved
add context adapter instead of none or ControlNet (ablation)S-Flow · InterHumanFID: 7.038 -> 4.772Improved
add context reconstruction loss (ablation)S-Flow · InterHumanFID: 5.765 -> 4.772Improved
use UMF instead of specialist TIMotionUMF vs TIMotion · InterHumanR-Precision Top3: 0.724 -> 0.694Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 5 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy