公开(公告)号：US20250148623A1

公开(公告)日：2025-05-08

申请号：US18921174

申请日：2024-10-21

Applicant: Apple Inc.

Inventor： Arnab Kumar Mondal ,  Stefano Alletto ,  Denis Tome' ,  Abhishek Narain

IPC: G06T7/246 ,  G06T17/20

Abstract: Various implementations disclosed herein include devices, systems, and methods that generate 3-dimensional (3D) information related to a user from a continuous time light signal. For example, a process may obtain two-dimensional (2D) information corresponding to a continuous time light signal providing information about a user in a 3D environment. The 2D information may be based on frames comprising images capturing the continuous time light signal at one or more frame rates. The process may further obtain discretization information corresponding to the one or more frame rates. The process may further determine 3D information about the user by inputting the 2D information and the discretization information into a state space model. The state space model may be a continuous time learnable framework for mapping between continuous time 2D scalar inputs and continuous time scalar 3D outputs.