Stanford researchers have created a single diffusion generative model, DiffusionPoser, that can reconstruct human motion in real-time from arbitrary body sensor configurations, with broad application in a variety of motion capture end uses.
Researchers in the Murmann Mixed Signal Group have developed a pipelined chip architecture with inverted residual and linear bottlenecks-based networks for energy efficient Machine Learning inference on edge devices.
Stanford researchers have developed a method called KleinPAT, for creating sound models in seconds, making it cost effective to simulate sounds for many different objects in a virtual environment.
Stanford researchers have patented a data-driven method for building a human shape model that spans variation in both subject shape and pose. The method is based on a representation that incorporates both articulated and non-rigid deformations.
Stanford researchers have patented an automated method for generating articulated human models consisting of both morphological and kinematic model data.
Researchers from Stanford University and the Max Planck Institute have patented a new marker-less approach to capturing human performances from multi-view video.