cs.CVNov 10, 2026

FlashMotion: Ultra-Fast Long-Term 3D Motion Generation

Authors: Kaixing Yang, Xulong Tang, Ronghui Li, Xiangyue Zhang, Ziqiao Peng, Mingshuang Luo, Chenxi Zhao, Haoyu Wu, 

Organizations: Renmin University of China, Beijing, China · The University of Texas at Dallas · Tsinghua University, Beijing, China · Wuhan University, Wuhan, China · 

Abstract

3D human motion generation plays a crucial role in game development, extended reality (XR), digital humans, and embodied simulation. Beyond motion generation, practical pipelines include rigging, retargeting, and rendering, making ultra-fast long-term 3D motion generation without compromising quality valuable for real-time interactive applications. Despite promising progress, high-quality long-horizon motion generation under tight inference budgets remains challenging, owing to 2 coupled bottlenecks: (1) generative strategies that require many sampling steps for high-quality 3D motion generation and (2) model architectures with substantial per-step computational and memory costs for long sequences. We present FlashMotion, a co-designed framework for high-quality long-horizon 3D motion generation under a strict inference budget, covering text-to-motion, music-to-dance, and speech-to-gesture tasks. To enhance trajectory-level efficiency, we introduce a 3D motion-space MeanFlow formulation with kinematic and dynamic consistency constraints for few-step generation, together with an Adaptive Soft masking mechanism for temporally coherent motion editing. To improve per-step efficiency, we design a lightweight non-autoregressive BiMamba architecture with condition-guided state selection and AdaIN-based condition fusion mechanism, enhancing cross-modal alignment and generalization to longer motion sequences. Extensive experiments demonstrate that FlashMotion achieves overall state-of-the-art performance in both quality and efficiency across text-to-motion, speech-to-gesture, and music-to-dance generation. The project page is available at https://sun-happy-ykx.github.io/FlashMotion-Project/

Figures & tables

Explore similar work

CardsList
  1. FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation

    Nov 26, 2025Kaixing Yang, Xulong Tang, Ziqiao Peng +4MeanFlowHuman Motion Generation

  2. ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

    Jul 9, 2026Kaifeng Zhao, Mathis Petrovich, Haotian Zhang +3Text-to-Motion GenerationHuman Motion Generation

  3. World2Motion: Turning Video World Models into 3D Human Motion Generators

    Sep 29, 2026Fangyuan Tu, Xiangyue Zhang, Yiyi Cai +8Human Motion GenerationDiffusion Models for Motion Generation