-
公开(公告)号：US10949715B1
公开(公告)日：2021-03-16
申请号：US16884485
申请日：2020-05-27
Applicant: Neon Evolution Inc.
Inventor： Cody Gustave Berlin , Carl Davis Bogan, III , Kenneth Michael Lande , Jacob Myles Laser , Brian Sung Lee , Anders Øland
Abstract: Systems and methods are disclosed configured to train an autoencoder using images that include faces, wherein the autoencoder comprises an input layer, an encoder configured to output a latent image from a corresponding input image, and a decoder configured to attempt to reconstruct the input image from the latent image. An image sequence of a face exhibiting a plurality of facial expressions and transitions between facial expressions is generated and accessed. Images of the plurality of facial expressions and transitions between facial expressions are captured from a plurality of different angles and using different lighting. An autoencoder is trained using source images that include the face with different facial expressions captured at different angles with different lighting, and using destination images that include a destination face. The trained autoencoder is used to generate an output where the likeness of the face in the destination images is swapped with the likeness of the source face, while preserving expressions of the destination face.
-
公开(公告)号：US20230049729A1
公开(公告)日：2023-02-16
申请号：US17658325
申请日：2022-04-07
Applicant: Neon Evolution Inc.
Inventor： Cody Gustave Berlin , Carl Davis Bogan, III , Kenneth Michael Lande , Anders Øland , Davide Toniolo , Alessia Bertugli , Dario Bertazioli , Brian Sung Lee
Abstract: Systems and methods are disclosed configured to train an autoencoder. A data training set is generated comprising images of different faces. A first autoencoder configuration is generated, comprising a first encoder, and a first decoder. The first autoencoder configuration is trained using dataset images, wherein weights associated with the first encoder and weights associated with the first decoder are modified. A second autoencoder configuration is generated comprising the first encoder and a second decoder. The second decoder is trained using images of a first target face. First encoder weights are substantially maintained, and weights associated with the second decoder are modified. An autoencoder comprising the trained first encoder and the trained second decoder generates an output using a source image of a first face having a facial expression, where the facial expression of the first face from the source image is applied to the first specific target face.
-
公开(公告)号：US11670024B2
公开(公告)日：2023-06-06
申请号：US17249637
申请日：2021-03-08
Applicant: Neon Evolution Inc.
Inventor： Cody Gustave Berlin , Carl Davis Bogan, III , Kenneth Michael Lande , Jacob Myles Laser , Brian Sung Lee , Anders Øland
IPC: G06K9/00 , G06T11/60 , G06T1/20 , G06T7/32 , G06V40/16 , G06F18/214 , G06V10/764 , G06V10/774 , G06V10/82 , G06V10/44
CPC classification number: G06T11/60 , G06F18/214 , G06T1/20 , G06T7/32 , G06V10/454 , G06V10/764 , G06V10/774 , G06V10/82 , G06V40/168 , G06V40/174 , G06T2207/20081
Abstract: Systems and methods are disclosed configured to train an autoencoder using images that include faces, wherein the autoencoder comprises an input layer, an encoder configured to output a latent image from a corresponding input image, and a decoder configured to attempt to reconstruct the input image from the latent image. An image sequence of a face exhibiting a plurality of facial expressions and transitions between facial expressions is generated and accessed. Images of the plurality of facial expressions and transitions between facial expressions are captured from a plurality of different angles and using different lighting. An autoencoder is trained using source images that include the face with different facial expressions captured at different angles with different lighting, and using destination images that include a destination face. The trained autoencoder is used to generate an output where the likeness of the face in the destination images is swapped with the likeness of the source face, while preserving expressions of the destination face.
-
公开(公告)号：US20210056348A1
公开(公告)日：2021-02-25
申请号：US16884485
申请日：2020-05-27
Applicant: Neon Evolution Inc.
Inventor： Cody Gustave Berlin , Carl Davis Bogan, III , Kenneth Michael Lande , Jacob Myles Laser , Brian Sung Lee , Anders Øland
Abstract: Systems and methods are disclosed configured to train an autoencoder using images that include faces, wherein the autoencoder comprises an input layer, an encoder configured to output a latent image from a corresponding input image, and a decoder configured to attempt to reconstruct the input image from the latent image. An image sequence of a face exhibiting a plurality of facial expressions and transitions between facial expressions is generated and accessed. Images of the plurality of facial expressions and transitions between facial expressions are captured from a plurality of different angles and using different lighting. An autoencoder is trained using source images that include the face with different facial expressions captured at different angles with different lighting, and using destination images that include a destination face. The trained autoencoder is used to generate an output where the likeness of the face in the destination images is swapped with the likeness of the source face, while preserving expressions of the destination face.
-
公开(公告)号：US11308657B1
公开(公告)日：2022-04-19
申请号：US17399962
申请日：2021-08-11
Applicant: Neon Evolution Inc.
Inventor： Cody Gustave Berlin , Carl Davis Bogan, III , Kenneth Michael Lande , Anders Øland , Davide Toniolo , Alessia Bertugli , Dario Bertazioli , Brian Sung Lee
IPC: G06T11/00 , G06K9/00 , G06T5/50 , G06N3/04 , G06N3/08 , G06K9/62 , G10L25/30 , G10L21/013 , G10L25/18
Abstract: Systems and methods are disclosed configured to train an autoencoder. A data training set is generated comprising images of different faces. A first autoencoder configuration is generated, comprising a first encoder, and a first decoder. The first autoencoder configuration is trained using dataset images, wherein weights associated with the first encoder and weights associated with the first decoder are modified. A second autoencoder configuration is generated comprising the first encoder and a second decoder. The second decoder is trained using a plurality of images of a first target face. First encoder weights are substantially maintained, and weights associated with the second decoder are modified. An autoencoder comprising the trained first encoder and the trained second decoder is used to generate an output using a source image of a first face having a facial expression, where the facial expression of the first face from the source image is applied to the first specific target face.
-
Patent Agency Ranking
公开(公告)号：US20210334595A1
公开(公告)日：2021-10-28
申请号：US17249637
申请日：2021-03-08
Applicant: Neon Evolution Inc.
Inventor： Cody Gustave Berlin , Carl Davis Bogan, III , Kenneth Michael Lande , Jacob Myles Laser , Brian Sung Lee , Anders Øland
Abstract: Systems and methods are disclosed configured to train an autoencoder using images that include faces, wherein the autoencoder comprises an input layer, an encoder configured to output a latent image from a corresponding input image, and a decoder configured to attempt to reconstruct the input image from the latent image. An image sequence of a face exhibiting a plurality of facial expressions and transitions between facial expressions is generated and accessed. Images of the plurality of facial expressions and transitions between facial expressions are captured from a plurality of different angles and using different lighting. An autoencoder is trained using source images that include the face with different facial expressions captured at different angles with different lighting, and using destination images that include a destination face. The trained autoencoder is used to generate an output where the likeness of the face in the destination images is swapped with the likeness of the source face, while preserving expressions of the destination face.
-
公开(公告)号：US10552667B1
公开(公告)日：2020-02-04
申请号：US16544673
申请日：2019-08-19
Applicant: Neon Evolution Inc.
Inventor： Carl Davis Bogan, III , Kenneth Michael Lande , Jacob Myles Laser , Brian Sung Lee
Abstract: Systems and methods are disclosed configured to pre-train an autoencoder using images that include faces, wherein the autoencoder comprises an input layer, an encoder configured to output a latent image from a corresponding input image, and a decoder configured to attempt to reconstruct the input image from the latent image. An image sequence of a CGI sculpted and textured face exhibiting a plurality of facial expressions and transitions between facial expressions is accessed. Images of the plurality of facial expressions and transitions between facial expressions are captured from a plurality of different angles. The pre-trained autoencoder is trained using source images that include a CGI face with different facial expressions captured at different angles, and using destination images that include a real face. The trained autoencoder is used to generate an output where the real face in the destination images is swapped with the CGI face, while preserving expressions of the real face.
-
公开(公告)号：US10803646B1
公开(公告)日：2020-10-13
申请号：US16700724
申请日：2019-12-02
Applicant: Neon Evolution Inc.
Inventor： Carl Davis Bogan, III , Kenneth Michael Lande , Jacob Myles Laser , Brian Sung Lee , Cody Gustave Berlin
Abstract: Systems and methods are disclosed configured to train an autoencoder using images that include faces, wherein the autoencoder comprises an input layer, an encoder configured to output a latent image from a corresponding input image, and a decoder configured to attempt to reconstruct the input image from the latent image. An image sequence of a face exhibiting a plurality of facial expressions and transitions between facial expressions is generated and accessed. Images of the plurality of facial expressions and transitions between facial expressions are captured from a plurality of different angles and using different lighting. An autoencoder is trained using source images that include the face with different facial expressions captured at different angles with different lighting, and using destination images that include a destination face. The trained autoencoder is used to generate an output where the likeness of the face in the destination images is swapped with the likeness of the source face, while preserving expressions of the destination face.
-
公开(公告)号：US10671838B1
公开(公告)日：2020-06-02
申请号：US16700684
申请日：2019-12-02
Applicant: Neon Evolution Inc.
Inventor： Carl Davis Bogan, III , Kenneth Michael Lande , Jacob Myles Laser , Brian Sung Lee , Cody Gustave Berlin
Abstract: Systems and methods are disclosed configured to train an autoencoder using images that include faces, wherein the autoencoder comprises an input layer, an encoder configured to output a latent image from a corresponding input image, and a decoder configured to attempt to reconstruct the input image from the latent image. An image sequence of a face exhibiting a plurality of facial expressions and transitions between facial expressions is generated and accessed. Images of the plurality of facial expressions and transitions between facial expressions are captured from a plurality of different angles and using different lighting. An autoencoder is trained using source images that include the face with different facial expressions captured at different angles with different lighting, and using destination images that include a destination face. The trained autoencoder is used to generate an output where the likeness of the face in the destination images is swapped with the likeness of the source face, while preserving expressions of the destination face.
-
公开(公告)号：US10658005B1
公开(公告)日：2020-05-19
申请号：US16700695
申请日：2019-12-02
Applicant: Neon Evolution Inc.
Inventor： Carl Davis Bogan, III , Kenneth Michael Lande , Jacob Myles Laser , Brian Sung Lee , Cody Gustave Berlin
IPC: G11B27/036 , G06K9/62 , G06K9/00 , G10L21/055 , G06T9/00 , G10L25/57 , G10L25/24
Abstract: Systems and methods are disclosed configured to train an autoencoder using images that include faces, wherein the autoencoder comprises an input layer, an encoder configured to output a latent image from a corresponding input image, and a decoder configured to attempt to reconstruct the input image from the latent image. An image sequence of a face exhibiting a plurality of facial expressions and transitions between facial expressions is generated and accessed. Images of the plurality of facial expressions and transitions between facial expressions are captured from a plurality of different angles and using different lighting. An autoencoder is trained using source images that include the face with different facial expressions captured at different angles with different lighting, and using destination images that include a destination face. The trained autoencoder is used to generate an output where the likeness of the face in the destination images is swapped with the likeness of the source face, while preserving expressions of the destination face.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.012 seconds)
