Teacher-Student Diffusion Model for Text-Driven 3D Hand Motion Generation

• URL: http://arxiv.org/abs/2603.24407v1
• Date: Wed, 25 Mar 2026 15:21:04 GMT
• Title: Teacher-Student Diffusion Model for Text-Driven 3D Hand Motion Generation
• Abstract summary: Existing methods either focus on full-body motion, overlooking detailed hand gestures, or require explicit 3D object meshes.<n>We propose TSHaMo, a model-agnostic teacher-student diffusion framework for text-driven hand motion generation.
• Score: 54.27025073220947
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Generating realistic 3D hand motion from natural language is vital for VR, robotics, and human-computer interaction. Existing methods either focus on full-body motion, overlooking detailed hand gestures, or require explicit 3D object meshes, limiting generality. We propose TSHaMo, a model-agnostic teacher-student diffusion framework for text-driven hand motion generation. The student model learns to synthesize motions from text alone, while the teacher leverages auxiliary signals (e.g., MANO parameters) to provide structured guidance during training. A co-training strategy enables the student to benefit from the teacher's intermediate predictions while remaining text-only at inference. Evaluated using two diffusion backbones on GRAB and H2O, TSHaMo consistently improves motion quality and diversity. Ablations confirm its robustness and flexibility in using diverse auxiliary inputs without requiring 3D objects at test time.

Related papers

• CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild [41.0322780136795]
  We introduce '3D Hands in the Wild' (3D-HIW), a dataset of 32K 3D hand-motion sequences and aligned text.<n>We then propose CLUTCH, an LLM-based hand animation system with two critical innovations: (a) SHIFT, a novel VQ-VAE architecture to tokenize hand motion, and (b) a geometric refinement stage to finetune the LLM.<n> Experiments demonstrate state-of-the-art performance on text-to-motion and motion-to-text tasks, establishing the first benchmark for scalable in-the-wild hand motion modelling
  arXiv  Detail & Related papers  (2026-02-19T19:02:22Z)
• Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance [48.986552871497]
  We introduce a novel two-stage framework that employs scene affordance as an intermediate representation. By leveraging scene affordance maps, our method overcomes the difficulty in generating human motion under multimodal condition signals. Our approach consistently outperforms all baselines on established benchmarks, including HumanML3D and HUMANISE.
  arXiv  Detail & Related papers  (2024-03-26T18:41:07Z)
• Motion Generation from Fine-grained Textual Descriptions [29.033358642532722]
  We build a large-scale language-motion dataset specializing in fine-grained textual descriptions, FineHumanML3D. We design a new text2motion model, FineMotionDiffuse, making full use of fine-grained textual information. Our evaluation shows that FineMotionDiffuse trained on FineHumanML3D improves FID by a large margin of 0.38, compared with competitive baselines.
  arXiv  Detail & Related papers  (2024-03-20T11:38:30Z)
• BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics [50.88842027976421]
  We propose BOTH57M, a novel multi-modal dataset for two-hand motion generation. Our dataset includes accurate motion tracking for the human body and hands. We also provide a strong baseline method, BOTH2Hands, for the novel task.
  arXiv  Detail & Related papers  (2023-12-13T07:30:19Z)
• AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism [24.049207982022214]
  We propose textbftT2M, a two-stage method with multi-perspective attention mechanism. Our method outperforms the current state-of-the-art in terms of qualitative and quantitative evaluation.
  arXiv  Detail & Related papers  (2023-09-02T02:18:17Z)
• Generating Holistic 3D Human Motion from Speech [97.11392166257791]
  We build a high-quality dataset of 3D holistic body meshes with synchronous speech. We then define a novel speech-to-motion generation framework in which the face, body, and hands are modeled separately.
  arXiv  Detail & Related papers  (2022-12-08T17:25:19Z)
• TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts [20.336481832461168]
  Inspired by the strong ties between vision and language, our paper aims to explore the generation of 3D human full-body motions from texts. We propose the use of motion token, a discrete and compact motion representation. Our approach is flexible, could be used for both text2motion and motion2text tasks.
  arXiv  Detail & Related papers  (2022-07-04T19:52:18Z)
• TEMOS: Generating diverse human motions from textual descriptions [53.85978336198444]
  We address the problem of generating diverse 3D human motions from textual descriptions. We propose TEMOS, a text-conditioned generative model leveraging variational autoencoder (VAE) training with human motion data. We show that TEMOS framework can produce both skeleton-based animations as in prior work, as well more expressive SMPL body motions.
  arXiv  Detail & Related papers  (2022-04-25T14:53:06Z)
• Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body Dynamics [87.17505994436308]
  We build upon the insight that body motion and hand gestures are strongly correlated in non-verbal communication settings. We formulate the learning of this prior as a prediction task of 3D hand shape over time given body motion input alone. Our hand prediction model produces convincing 3D hand gestures given only the 3D motion of the speaker's arms as input.
  arXiv  Detail & Related papers  (2020-07-23T22:58:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.