Spreeai Corporation

Spree3d Corporation

Evan Smyth

Gil Spencer

Dmitriy Vladlenovich Pinskiy

Robert Meyer Davidson

Systems and methods for generating and simultaneously displaying multiple photorealistic digital avatars wearing garments. One specific method embodiment comprises the steps of: receiving a selection of one or more garments from a user; producing an electronic avatar for each of the selected garments; retrieving a plurality of body measurements of the user; generating a multi-dimensional space based upon the plurality of body measurements of the user; generating an interpolation measurement space for each electronic avatar for each of the selected garments, with each avatar wearing a selected garment; interpolating between two avatars to generate a realistic customized electronic avatar of the user wearing one of the garments; adding photorealistic imagery of the user's face and hair to each rendered customized animated garmented avatar to create a complete digital garmented avatar for the user for each of the selected garments; transmitting each complete digital garmented avatar to a user device; and simultaneously displaying on the user device each complete digital garmented avatar.

Generation and simultaneous display of multiple digitally garmented avatars

Methods and apparati for using an avatar () to help produce a digital image representation () of a body (). A method embodiment of the present invention comprises the steps of capturing () measurements of the body () and combining the measurements with an avatar () to produce a set of avatar images (); invoking () a neural network () to generate a set of photorealistic face and hair images (); combining () the avatar images () and the face and hair images () to produce a set of composite images (); and converting () the set of composite images () into a set of final images () representing the body ().

Producing a digital image representation of a body

Provided are methods and systems for automatic creation of a customized avatar animation of a user. An example method commences with receiving production parameters and creating, based on the production parameters, a multidimensional array of a plurality of blank avatar animations. Each blank avatar animation has a predetermined number of frames and a plurality of features associated with each frame. The method further includes receiving user parameters including body dimensions, hair, and images of a face of a user. The method continues with selecting, from the plurality of blank avatar animations, two blank avatar animations closest to the user based on the body dimensions. The method further includes interpolating corresponding frames of the two blank avatar animations to produce an interpolated avatar animation. The method continues with compositing the face and the hair with the interpolated avatar animation using a machine learning technique to render the customized avatar animation.

Growing community of inventors

La Crescenta, CA, United States of America

Evan Smyth