Abstract: A computing system may receive sensor data from one or more sensors coupled to a user. Based on sensor data, the computing system may generate an upper body pose that corresponds to a first portion of a body of the user, which comprises a head and an arm of the user. The computing system may determine contextual information associated with the user. The computing system may generate a lower body pose corresponding to a second portion of the body of the user comprising a leg of the user based on the upper body pose and the contextual information. The computing system may generate a full body pose of the user based on the first upper body pose and the lower body pose.

Abstract: A computing system may receive sensor data from one or more sensors coupled to a user. Based on sensor data, the computing system may generate a first upper body pose that corresponds to a first portion of a body of the user, which comprises a head and an arm of the user. The computing system may process the upper body pose of the user to generate a temporal sequence of lower body poses comprising a first lower body pose associated with the first time and a second lower body pose associated with a second time, which may correspond to a second portion of the body of the user comprising a leg of the user. The computing system may generate one or more full body poses of the user based on at least the first upper body pose and the temporal sequence of lower body poses.

Abstract: In one embodiment, a method includes adjusting parameters of a three-dimensional geometry corresponding to a first person to make the three-dimensional geometry represent a desired pose for the first person, accessing a neural texture encoding an appearance of the first person, generating a first rendered neural texture based on a mapping between (1) a portion of the three-dimensional geometry that is visible from a viewing direction and (2) the neural texture, generating a second rendered neural texture by processing the first rendered neural texture using a first neural network, determining normal information associated with the portion of the three-dimensional geometry that is visible from the viewing direction, and generating a rendered image for the first person in the desired pose by processing the second rendered neural texture and the normal information using a second neural network.

Abstract: A computing system may receive sensor data from one or more sensors coupled to a user. Based on sensor data, the computing system may generate a first upper body pose that corresponds to a first portion of a body of the user, which comprises a head and an arm of the user. The computing system may process the upper body pose of the user to generate a temporal sequence of lower body poses comprising a first lower body pose associated with the first time and a second lower body pose associated with a second time, which may correspond to a second portion of the body of the user comprising a leg of the user. The computing system may generate one or more full body poses of the user based on at least the first upper body pose and the temporal sequence of lower body poses.

Abstract: A computing system may receive sensor data from one or more sensors coupled to a user. Based on this sensor data, the computing system may generate an upper body pose that corresponds to a first portion of a body of the user, which may comprise a head and an arm of the user. The computing system may process the upper body pose of the user using a machine learning model to generate a lower body pose that corresponds to a second portion of the body of the user, which may comprise a leg of the user. The computing system may generate a full body pose of the user based on the upper body pose and the lower body pose.

Abstract: A computing system may receive sensor data from one or more sensors coupled to a user. Based on this sensor data, the computing system may generate an upper body pose that corresponds to a first portion of a body of the user, which may comprise a head and an arm of the user. The computing system may process the upper body pose of the user using a machine learning model to generate a lower body pose that corresponds to a second portion of the body of the user, which may comprise a leg of the user. The computing system may generate a full body pose of the user based on the upper body pose and the lower body pose.

Abstract: In one embodiment, a method includes adjusting parameters of a three-dimensional geometry corresponding to a first person to make the three-dimensional geometry represent a desired pose for the first person, accessing a neural texture encoding an appearance of the first person, generating a first rendered neural texture based on a mapping between (1) a portion of the three-dimensional geometry that is visible from a viewing direction and (2) the neural texture, generating a second rendered neural texture by processing the first rendered neural texture using a first neural network, determining normal information associated with the portion of the three-dimensional geometry that is visible from the viewing direction, and generating a rendered image for the first person in the desired pose by processing the second rendered neural texture and the normal information using a second neural network.

Abstract: Artificial reality (AR) systems track pose and skeletal positioning for multiple co-located participants, each having a head mounted display (HMD). Participants can join a shared artificial reality event or experience with others in the same location. Each participant's HMD can independently render AR content for the participant based on the participant's pose and pose information obtained from other participants' HMDs. A participating HMD may broadcast tracking estimates for skeletal points of interest (e.g., joints, finger tips, knees, ankle points, etc.) that are within the field-of-view of the HMD's cameras and/or sensors. A participating HMD may receive skeletal position information determined by other HMDs, and aggregate the received tracking information along with internal tracking information to construct an accurate, full estimate of its own pose and skeletal positioning information for its corresponding participant.

Abstract: Artificial reality (AR) systems track pose and skeletal positioning for multiple co-located participants, each having a head mounted display (HMD). Participants can join a shared artificial reality event or experience with others in the same location. Each participant's HMD can independently render AR content for the participant based on the participant's pose and pose information obtained from other participants' HMDs. A participating HMD may broadcast tracking estimates for skeletal points of interest (e.g., joints, finger tips, knees, ankle points, etc.) that are within the field-of-view of the HMD's cameras and/or sensors. A participating HMD may receive skeletal position information determined by other HMDs, and aggregate the received tracking information along with internal tracking information to construct an accurate, full estimate of its own pose and skeletal positioning information for its corresponding participant.