Research

Paper

AI LLM February 19, 2026

CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild

Authors

Balamurugan Thambiraja, Omid Taheri, Radek Danecek, Giorgio Becherini, Gerard Pons-Moll, Justus Thies

Abstract

Hands play a central role in daily life, yet modeling natural hand motions remains underexplored. Existing methods that tackle text-to-hand-motion generation or hand animation captioning rely on studio-captured datasets with limited actions and contexts, making them costly to scale to "in-the-wild" settings. Further, contemporary models and their training schemes struggle to capture animation fidelity with text-motion alignment. To address this, we (1) introduce '3D Hands in the Wild' (3D-HIW), a dataset of 32K 3D hand-motion sequences and aligned text, and (2) 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. To build 3D-HIW, we propose a data annotation pipeline that combines vision-language models (VLMs) and state-of-the-art 3D hand trackers, and apply it to a large corpus of egocentric action videos covering a wide range of scenarios. To fully capture motion in-the-wild, CLUTCH employs SHIFT, a part-modality decomposed VQ-VAE, which improves generalization and reconstruction fidelity. Finally, to improve animation quality, we introduce a geometric refinement stage, where CLUTCH is co-supervised with a reconstruction loss applied directly to decoded hand motion parameters. 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. Code, data and models will be released.

Metadata

arXiv ID: 2602.17770
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-02-19
Fetched: 2026-02-23 05:33

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.17770v1</id>\n    <title>CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild</title>\n    <updated>2026-02-19T19:02:22Z</updated>\n    <link href='https://arxiv.org/abs/2602.17770v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.17770v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Hands play a central role in daily life, yet modeling natural hand motions remains underexplored. Existing methods that tackle text-to-hand-motion generation or hand animation captioning rely on studio-captured datasets with limited actions and contexts, making them costly to scale to \"in-the-wild\" settings. Further, contemporary models and their training schemes struggle to capture animation fidelity with text-motion alignment. To address this, we (1) introduce '3D Hands in the Wild' (3D-HIW), a dataset of 32K 3D hand-motion sequences and aligned text, and (2) 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. To build 3D-HIW, we propose a data annotation pipeline that combines vision-language models (VLMs) and state-of-the-art 3D hand trackers, and apply it to a large corpus of egocentric action videos covering a wide range of scenarios. To fully capture motion in-the-wild, CLUTCH employs SHIFT, a part-modality decomposed VQ-VAE, which improves generalization and reconstruction fidelity. Finally, to improve animation quality, we introduce a geometric refinement stage, where CLUTCH is co-supervised with a reconstruction loss applied directly to decoded hand motion parameters. 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. Code, data and models will be released.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-02-19T19:02:22Z</published>\n    <arxiv:comment>ICLR2026; Project page: https://balamuruganthambiraja.github.io/CLUTCH/</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Balamurugan Thambiraja</name>\n    </author>\n    <author>\n      <name>Omid Taheri</name>\n    </author>\n    <author>\n      <name>Radek Danecek</name>\n    </author>\n    <author>\n      <name>Giorgio Becherini</name>\n    </author>\n    <author>\n      <name>Gerard Pons-Moll</name>\n    </author>\n    <author>\n      <name>Justus Thies</name>\n    </author>\n  </entry>"
}