Lune

CVPR2026Top-tier venue

MotionMaster: Generalizable Text-Driven Motion Generation and Editing

Nan Jiang, Yunhao Li, Lexi Pang, Zimo He, Siyuan Huang, Yixin Zhu

Abstract

Synthesizing realistic human motion from natural language holds transformative potential for animation, robotics, and virtual reality. Recent methods handle single-action sequences and simple textual instructions, yet multi-action compositions and precise editing remain elusive due to limited data diversity, inadequate representations, and fragmented pipelines. Critically, most existing methods train motion generation models from scratch, failing to exploit the rich action semantics and long-horizon reasoning already encoded in pretrained Multimodal Large Language Models (MLLMs). Here we show that finetuning a pretrained MLLM with large-scale motion data yields strong zero-shot generalization across diverse text-guided motion generation and editing tasks. We present MotionMaster, a unified framework built on three components: MotionGB, a 10,000-hour dataset expanded from 400 hours of verified motion capture via spatial-temporal augmentation; an FSQ-based tokenizer that preserves both local joint accuracy and global trajectory coherence; and a finetuned MLLM with motion and language tokens in a shared embedding space. MotionMaster outperforms prior methods by 41.6% in multi-action semantic consistency and 20.8% in body-part composition. These results demonstrate that pretraining knowledge from MLLMs transfers effectively to motion understanding, opening a viable path toward general-purpose motion intelligence.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Action-Conditioned 3D Human Motion Synthesis with Transformer VAE cites Action2Motion: Conditioned Generation of 3D Human Motions
  • Action-Conditioned 3D Human Motion Synthesis with Transformer VAE cites AMASS: Archive of Motion Capture As Surface Shapes
  • Generating Diverse and Natural 3D Human Motions from Text cites Action-Conditioned 3D Human Motion Synthesis with Transformer VAE
  • Generating Diverse and Natural 3D Human Motions from Text cites Action2Motion: Conditioned Generation of 3D Human Motions
  • Generating Diverse and Natural 3D Human Motions from Text cites AMASS: Archive of Motion Capture As Surface Shapes
  • MotionGPT: Human Motion as a Foreign Language cites Action-Conditioned 3D Human Motion Synthesis with Transformer VAE
  • MotionGPT: Human Motion as a Foreign Language cites Action2Motion: Conditioned Generation of 3D Human Motions
  • MotionGPT: Human Motion as a Foreign Language cites Generating Diverse and Natural 3D Human Motions from Text
  • MotionGPT: Human Motion as a Foreign Language cites AMASS: Archive of Motion Capture As Surface Shapes
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on36

  1. AMASS: Archive of Motion Capture As Surface ShapesNaureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll et al.ICCV 2019 · 1,784 citations
  2. MotionGPT: Human Motion as a Foreign LanguageBiao Jiang, Xin Chen, Wen Liu, Jingyi Yu et al.NeurIPS 2023 · 698 citations
  3. Action-Conditioned 3D Human Motion Synthesis with Transformer VAEMathis Petrovich, Michael J. Black, Gül VarolICCV 2021 · 672 citations
  4. Generating Diverse and Natural 3D Human Motions from TextChuan Guo, Shihao Zou, Xinxin Zuo, Sen Wang et al.CVPR 2022 · 462 citations
  5. Action2Motion: Conditioned Generation of 3D Human MotionsChuan Guo, Xinxin Zuo, Sen Wang, Shihao Zou et al.ACM MM 2020 · 394 citations

Related papers

  1. GenM3: Generative Pretrained Multi-Path Motion Model for Text Conditional Human Motion GenerationJunyu Shi, Lijiang Liu, Yong Sun, Zhiyuan Zhang et al.ICCV 2025 · 8 citations
  2. MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple GranularitiesBizhu Wu, Jinheng Xie, Keming Shen, Zhe Kong et al.CVPR 2025
  3. LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive TokensZekun Li, Sizhe An, Chengcheng Tang, Chuan Guo et al.CVPR 2026 · 12 citations
  4. Go to Zero: Towards Zero-Shot Motion Generation with Million-Scale DataKe Fan, Shunlin Lu, Minyue Dai, Runyi Yu et al.ICCV 2025 · 11 citations
  5. A Motion is Worth a Hybrid Sentence: Taming Language Model for Unified Motion Generation by Fine-grained PlanningRonghui Li, Lingxiao Han, Shi Shu, Yueyao Liu et al.ACM MM 2025
Dusk over the sea between two cliffs drawn in fine vertical lines