Abstract: Artificial reality (XR) experiences today typically only provide users representations of their upper body (e.g., as avatars). Although legs do not have a high range of movement or expression in XR, they are required to bring a sense of believability to digital humans represented in XR. However, tracking legs can be difficult because they are frequently not visible to XR device cameras. Aspects of the present disclosure provide a full body synthesis system that can generate plausible full body poses of users by leveraging generative machine learning, in real time, on an XR device. The full body synthesis system can be flexible to multiple numbers and types of inputs (e.g., positions/rotations/accelerations of joints, computer vision models, etc.), and can generalize users of any height, body scale, and body shape.

Abstract: An electronic device and a method for human segmentation in an image are provided. The method includes obtaining the image comprising at least one human, performing face detection to detect the human in the image, generating a first human segmentation from the image by comparing a pre-defined full human body template and the detected human, generating a second human segmentation from the image, by inputting the image to an artificial intelligence trained model and obtaining a composite human segmentation representing the detected human by using both of the first human segmentation and the second human segmentation.