Predicting body motion

An apparatus comprising a processor and a memory, the memory storing a trained generative motion model and instructions, which when executed by the processor cause the apparatus to, for a time step in a plurality of time steps:

• receive a reference joint pose of an articulated entity;
• receive an indication that a second joint of the articulated entity is unobserved or observed;
• and
• prompt a trained generative motion model, using the reference joint pose and a mask token, to predict body motion comprising a trajectory of the articulated entity and a pose of a joint of a plurality of joints of the articulated entity,
• wherein the mask token is temporally adaptable to generate temporally coherent motion of the second joint by:
• in response to receiving an indication that the second joint is unobserved, using information about the reference joint pose and a pose of the second joint from a previous time step;
• and
• in response to receiving an indication that the second joint is observed, using information about the reference joint pose and a pose of the second joint from a current time step.

A non-transitory computer-readable media storing computer-readable instructions which, when executed by a processor, cause the processor to perform operations comprising:

• receiving a reference joint pose of an articulated entity;
• receiving an indication that a second joint of the articulated entity is unobserved or observed;
• and
• prompting a trained generative motion model, using the reference joint pose and a mask token, to predict body motion comprising a trajectory of the articulated entity and a pose of a joint of a plurality of joints of the articulated entity,
• wherein the mask token is temporally adaptable to generate temporally coherent motion of the second joint by:
• in response to receiving an indication that the second joint is unobserved, using information about the reference joint pose and a pose of the second joint from a previous time step, and
• in response to receiving an indication that the second joint is observed, using information about the reference joint pose and a pose of the second joint from a current time step.