公开(公告)号：US20190340419A1

公开(公告)日：2019-11-07

申请号：US15970831

申请日：2018-05-03

Applicant: Adobe Inc.

Inventor： Rebecca Ilene Milman ,  Jose Ignacio Echevarria Vallespi ,  Jingwan Lu ,  Elya Shechtman ,  Duygu Ceylan Aksit ,  David P. Simons

IPC: G06K9/00 ,  G06T13/40 ,  G06T19/00 ,  G06F15/18

Abstract: Generation of parameterized avatars is described. An avatar generation system uses a trained machine-learning model to generate a parameterized avatar, from which digital visual content (e.g., images, videos, augmented and/or virtual reality (AR/VR) content) can be generated. The machine-learning model is trained to identify cartoon features of a particular style—from a library of these cartoon features—that correspond to features of a person depicted in a digital photograph. The parameterized avatar is data (e.g., a feature vector) that indicates the cartoon features identified from the library by the trained machine-learning model for the depicted person. This parameterization enables the avatar to be animated. The parameterization also enables the avatar generation system to generate avatars in non-photorealistic (relatively cartoony) styles such that, despite the style, the avatars preserve identities and expressions of persons depicted in input digital photographs.

公开(公告)号：US10607065B2

公开(公告)日：2020-03-31

申请号：US15970831

申请日：2018-05-03

Applicant: Adobe Inc.

Inventor： Rebecca Ilene Milman ,  Jose Ignacio Echevarria Vallespi ,  Jingwan Lu ,  Elya Shechtman ,  Duygu Ceylan Aksit ,  David P. Simons

IPC: G06K9/00 ,  G06T19/00 ,  G06T13/40 ,  G06N20/00

Abstract: Generation of parameterized avatars is described. An avatar generation system uses a trained machine-learning model to generate a parameterized avatar, from which digital visual content (e.g., images, videos, augmented and/or virtual reality (AR/VR) content) can be generated. The machine-learning model is trained to identify cartoon features of a particular style—from a library of these cartoon features—that correspond to features of a person depicted in a digital photograph. The parameterized avatar is data (e.g., a feature vector) that indicates the cartoon features identified from the library by the trained machine-learning model for the depicted person. This parameterization enables the avatar to be animated. The parameterization also enables the avatar generation system to generate avatars in non-photorealistic (relatively cartoony) styles such that, despite the style, the avatars preserve identities and expressions of persons depicted in input digital photographs.