LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment

arXiv:2403.13307v1 Announce Type: new
Abstract: Language-guided scene-aware human motion generation has great significance for entertainment and robotics. In response to the limitations of existing datasets, we introduce LaserHuman, a pioneering dataset engineered to revolutionize Scene-Text-to-Motion research. LaserHuman stands out with its inclusion of genuine human motions within 3D environments, unbounded free-form natural language descriptions, a blend of indoor and outdoor scenarios, and dynamic, ever-changing scenes. Diverse modalities of capture data and rich annotations present great opportunities for the research of …

abstract arxiv cs.cv dataset datasets entertainment environment environments form free human inclusion language limitations research robotics significance text type