الباحثون

Yangsong Zhang

المنشورات 2

نسخة أولية وصول مفتوح

Streaming Multi-Track Timeline Control for 3D Human Motion Generation

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 …

نسخة أولية وصول مفتوح

PACT: End-to-End Learning of Human Pose, Contacts, and Forces from Video

Human motion, environmental contacts, and interaction forces are governed by common physical laws, yet existing approaches typically separate visual pose reconstruction from contact and force estimation. This separation limits joint reasoning and can propagate errors between stages. We introduce PACT, an end-to-end mod …

المؤلفون المشاركون