3D人間動作生成のためのストリーミング・マルチトラック・タイムライン制御
Streaming Multi-Track Timeline Control for 3D Human Motion Generation
歩きながら電話に出るなど、進行中の動作に新しい指示を重ねてリアルタイムに3D人間動作を生成する手法を提案し、重複する指示区間と身体部位注釈付きデータセットも構築した。
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: Yangsong Zhang, Anujith Muraleedharan, Rikhat Akizhanov, Gül Varol, Fabio Pizzati, Ivan Laptev
分類: cs.CV, cs.AI, cs.LG
原文アブストラクト
Text-driven human motion generation has advanced substantially, yet most methods assume instructions are available before synthesis. Interactive applications require responding to new instructions while continuing ongoing actions, such as answering a phone while walking. Existing approaches address streaming generation or simultaneous composition without explicitly combining streaming instruction arrival with independently timed, overlapping actions. We introduce streaming multi-track timeline control and propose TimelineControl to incorporate new instructions alongside ongoing actions. Interval-aware conditioning preserves instruction timing, while causal part-structured representations and part-aware denoising coordinate concurrent actions across body regions. We also construct TimelineMotion, a dataset with overlapping instruction intervals and body-part annotations. Experiments on TimelineMotion and MTT demonstrate improved semantic alignment and temporal adherence over evaluated streaming baselines, including models retrained on the same data. Ablations and human evaluations validate our design, complemented by spatial conditioning and humanoid execution demonstrations. Our code, data and models will become publicly available.
