Multi-person 3D pose estimation

A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:

• acquire sensor data from at least cameras that are uncalibrated including images with depth information of a surrounding environment that includes multiple people;
• determine 2D poses and 3D features for the people according to the sensor data;
• generate camera poses using at least the depth information and the 3D features for cameras that generated the images including instructions to produce an essential matrix defining transformations between each of the cameras;
• generate 3D poses for the people according to the camera poses and the 3D features;
• and
• provide the 3D poses of the people.

A method, comprising:

• acquiring sensor data including images with depth information of a surrounding environment that includes multiple people, including acquiring the sensor data from sensors, including at least cameras that are uncalibrated;
• determining 2D poses and 3D features for the people according to the sensor data;
• generating camera poses using at least the depth information and the 3D features for the cameras that generated the images including producing an essential matrix defining transformations between each of the cameras;
• generating 3D poses for the people according to the camera poses and the 3D features;
• and
• providing the 3D poses of the people.