This software is a transformative technology in the fields of AI and digital image processing, offering a breakthrough approach to convolution, particularly for large-scale images.
Stanford researchers have patented an automated method for generating articulated human models consisting of both morphological and kinematic model data.
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.
This portfolio of inventions provides the tools for an advanced navigational system and panoramic virtual tours – technology that is incorporated in Google Street View.
Researchers from Stanford University and the Max Planck Institute have patented a new marker-less approach to capturing human performances from multi-view video.
Voice to Text and Sketch (V2TS) is a patented software program which allows text or drawings to be synchronized to recorded audio. Each portion of text or section of a drawing is associated with an audio segment recorded at the time it was written/sketched.
Stanford researchers have designed an intelligent software system that assists users by suggesting furniture arrangements that are based on interior design guidelines.
Stanford researchers have created software to view panoramic videos from arbitrary viewpoints from separate non-overlapping geo-referenced panoramic video streams. Ths system can also synthesize missing panoramic images to provide the user with a full sequence.
This user interface enables a user to define tags within virtual tour applications that label objects in panoramic images and video – a process that has been very difficult to achieve prior to this invention.