Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control
This addresses the need for more responsive generative models in XR for users, though it appears incremental as it builds on existing diffusion transformer methods with new conditioning mechanisms.
The paper tackles the problem of creating interactive video world models that respond to detailed human motion for extended reality applications, introducing a system that conditions on tracked head and hand poses to enable dexterous hand-object interactions. The result is a distilled causal system that improves human task performance and significantly increases perceived control compared to baselines.
Extended reality (XR) demands generative models that respond to users' tracked real-world motion, yet current video world models accept only coarse control signals such as text or keyboard input, limiting their utility for embodied interaction. We introduce a human-centric video world model that is conditioned on both tracked head pose and joint-level hand poses. For this purpose, we evaluate existing diffusion transformer conditioning strategies and propose an effective mechanism for 3D head and hand control, enabling dexterous hand--object interactions. We train a bidirectional video diffusion model teacher using this strategy and distill it into a causal, interactive system that generates egocentric virtual environments. We evaluate this generated reality system with human subjects and demonstrate improved task performance as well as a significantly higher level of perceived amount of control over the performed actions compared with relevant baselines.