LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment
This addresses the need for better scene-aware human motion generation in entertainment and robotics, but it is incremental as it builds on existing datasets and methods.
The authors tackled the problem of generating human motions from language descriptions in 3D scenes by introducing LaserHuman, a new dataset with free-form language and diverse environments, and proposed a multi-conditional diffusion model that achieved state-of-the-art performance on existing datasets.
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 conditional motion generation, and can also facilitate the development of real-life applications. Moreover, to generate semantically consistent and physically plausible human motions, we propose a multi-conditional diffusion model, which is simple but effective, achieving state-of-the-art performance on existing datasets.