空間に根ざしたジェスチャー生成：言語・動作・空間の統合
Grounded Gesture Generation: Language, Motion, and Space
空間的な文脈を考慮した指示的ジェスチャー生成のためのマルチモーダルデータセットとフレームワークを提案し、物理シミュレータと連携して状況に応じた評価を可能にした。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Anna Deichler, Jim O'Regan, Teo Guichoux, David Johansson, Jonas Beskow
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
Human motion generation has advanced rapidly in recent years, yet the critical problem of creating spatially grounded, context-aware gestures has been largely overlooked. Existing models typically specialize either in descriptive motion generation, such as locomotion and object interaction, or in isolated co-speech gesture synthesis aligned with utterance semantics. However, both lines of work often treat motion and environmental grounding separately, limiting advances toward embodied, communicative agents. To address this gap, our work introduces a multimodal dataset and framework for grounded gesture generation, combining two key resources: (1) a synthetic dataset of spatially grounded referential gestures, and (2) MM-Conv, a VR-based dataset capturing two-party dialogues. Together, they provide over 7.7 hours of synchronized motion, speech, and 3D scene information, standardized in the HumanML3D format. Our framework further connects to a physics-based simulator, enabling synthetic data generation and situated evaluation. By bridging gesture modeling and spatial grounding, our contribution establishes a foundation for advancing research in situated gesture generation and grounded multimodal interaction. Project page: https://groundedgestures.github.io/
