公开(公告)号：US20220374649A1

公开(公告)日：2022-11-24

申请号：US17484681

申请日：2021-09-24

申请人： DISNEY ENTERPRISES, INC. ,  ETH Zurich (Eidgenossische Technische Hochschule Zurich)

发明人： Jacek Krzysztof NARUNIEC ,  Derek Edward BRADLEY ,  Paulo Fabiano Urnau GOTARDO ,  Leonhard Markus HELMINGER ,  Christopher Andreas OTTO ,  Christopher Richard SCHROERS ,  Romann Matthew WEBER

IPC分类号： G06K9/62 ,  G06T11/00 ,  G06T17/20 ,  G06N3/04 ,  G06N3/08

摘要： Various embodiments set forth systems and techniques for changing a face within an image. The techniques include receiving a first image including a face associated with a first facial identity; generating, via a machine learning model, at least a first texture map and a first position map based on the first image; rendering a second image including a face associated with a second facial identity based on the first texture map and the first position map, wherein the second facial identity is different from the first facial identity.

公开(公告)号：US20210327038A1

公开(公告)日：2021-10-21

申请号：US16850898

申请日：2020-04-16

申请人： DISNEY ENTERPRISES, INC. ,  ETH Zürich (Eidgenössische Technische Hochschule Zürich)

发明人： Leonard Markus HELMINGER ,  Jacek Krzysztof NARUNIEC ,  Romann Matthew WEBER ,  Christopher Richard SCHROERS

IPC分类号： G06T5/20 ,  G06T9/00 ,  G06K9/00

摘要： Techniques are disclosed for changing the identities of faces in images. In embodiments, a tunable model for changing facial identities in images includes an encoder, a decoder, and dense layers that generate either adaptive instance normalization (AdaIN) coefficients that control the operation of convolution layers in the decoder or the values of weights within such convolution layers, allowing the model to change the identity of a face in an image based on a user selection. A separate set of dense layers may be trained to generate AdaIN coefficients for each of a number of facial identities, and the AdaIN coefficients output by different sets of dense layers can be combined to interpolate between facial identities. Alternatively, a single set of dense layers may be trained to take as input an identity vector and output AdaIN coefficients or values of weighs within convolution layers of the decoder.

公开(公告)号：US20220058822A1

公开(公告)日：2022-02-24

申请号：US17000755

申请日：2020-08-24

申请人： DISNEY ENTERPRISES, INC.

发明人： Jacek Krzysztof NARUNIEC ,  Christopher Richard SCHROERS ,  Romann Matthew WEBER

IPC分类号： G06T7/73 ,  G06T3/00 ,  G06T3/40 ,  G06T3/60 ,  G06T3/20 ,  G06K9/00 ,  G06K9/62 ,  G06N20/00 ,  G06N5/04

摘要： Various embodiments set forth systems and techniques for training a landmark model. The techniques include determining, using the landmark model, a first landmark in a set of first landmarks associated with a first image; performing, on the first image, a first perturbation to obtain a second image; determining, using the landmark model, a second landmark in a set of second landmarks associated with the second image; determining, based on a first distance between the first landmark and the second landmark, a first loss function; and updating, based on the first loss function, a first parameter of the landmark model.