cs.CVNov 6, 2026

PoseRieFlow: Riemannian Flow Matching for Whole-Body Text-to-Pose Generation

Authors: Jan Spindler, Bardia Ardakanian, Patrick Stotko, Reinhard Klein

Organizations: University of Bonn

Abstract

We present PoseRieFlow, a compact flow-matching framework for text-conditioned generation of whole-body 3D human poses. Prior text-to-pose methods either neglect articulated hands or model rotations in Euclidean space despite their non-Euclidean geometry. PoseRieFlow instead formulates generation directly on the product manifold of SMPL-H joint rotations, learning a text-conditioned vector field that transports samples from an isotropic SO(3)\mathrm{SO}(3) Gaussian prior to the data distribution along Riemannian geodesics. A part-tokenized Diffusion Transformer aggregates the 52 joints into eight body-part tokens, allocating a dedicated token and nonlinear projector to each hand, and restores per-joint resolution through part-specific decoders, shortening the sequence while improving kinematic fidelity over per-joint tokenization. With only 21.6M trainable parameters, PoseRieFlow supports expressive SMPL-H generation with detailed hand articulation at a fraction of the scale of recent LLM-based generators. On PoseScript, it attains the lowest whole-body kinematic error among all hand-producing methods, with consistent kinematic gains from the Riemannian formulation over its Euclidean counterpart at every practical inference budget, while distributional and retrieval metrics remain comparable between them.

Figures & tables

Explore similar work

CardsList
  1. MotionHiFlow: Text-to-motion via hierarchical flow matching

    Apr 25, 2026Heng Li, Xiaotong Lin, Ling-An Zeng +3Flow MatchingText-to-Motion Generation

  2. PRISM: Streaming Human Motion Generation with Per-Joint Latent Decomposition

    Mar 9, 2026Zeyu Ling, Qing Shuai, Teng Zhang +3Text-to-Motion GenerationHuman Motion Generation

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

    Apr 13, 2026Dawei Guan, Di Yang, Chengjie Jin +1Text-to-Motion GenerationHuman Motion Generation