公开(公告)号：US20230154088A1

公开(公告)日：2023-05-18

申请号：US17455318

申请日：2021-11-17

Applicant: ADOBE INC.

Inventor： Kevin Duarte ,  Wei-An Lin ,  Ratheesh Kalarot ,  Shabnam Ghadar ,  Jingwan Lu ,  Elya Shechtman ,  John Thomas Nack

IPC: G06T13/40 ,  G06T5/50 ,  G06N3/04

CPC classification number: G06T13/40 ,  G06N3/0454 ,  G06T5/50

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure encode features of a source image to obtain a source appearance encoding that represents inherent attributes of a face in the source image; encode features of a target image to obtain a target non-appearance encoding that represents contextual attributes of the target image; combine the source appearance encoding and the target non-appearance encoding to obtain combined image features; and generate a modified target image based on the combined image features, wherein the modified target image includes the inherent attributes of the face in the source image together with the contextual attributes of the target image.

公开(公告)号：US20230162407A1

公开(公告)日：2023-05-25

申请号：US17455796

申请日：2021-11-19

Applicant: ADOBE INC.

Inventor： Ratheesh Kalarot ,  Timothy M. Converse ,  Shabnam Ghadar ,  John Thomas Nack ,  Jingwan Lu ,  Elya Shechtman ,  Baldo Faieta ,  Akhilesh Kumar

IPC: G06T11/00 ,  G06K9/00 ,  G06N3/08

CPC classification number: G06T11/00 ,  G06K9/00288 ,  G06K9/00268 ,  G06N3/08

Abstract: The present disclosure describes systems and methods for image processing. Embodiments of the present disclosure include an image processing apparatus configured to generate modified images (e.g., synthetic faces) by conditionally changing attributes or landmarks of an input image. A machine learning model of the image processing apparatus encodes the input image to obtain a joint conditional vector that represents attributes and landmarks of the input image in a vector space. The joint conditional vector is then modified, according to the techniques described herein, to form a latent vector used to generate a modified image. In some cases, the machine learning model is trained using a generative adversarial network (GAN) with a normalization technique, followed by joint training of a landmark embedding and attribute embedding (e.g., to reduce inference time).

公开(公告)号：US11900519B2

公开(公告)日：2024-02-13

申请号：US17455318

申请日：2021-11-17

Applicant: ADOBE INC.

Inventor： Kevin Duarte ,  Wei-An Lin ,  Ratheesh Kalarot ,  Shabnam Ghadar ,  Jingwan Lu ,  Elya Shechtman ,  John Thomas Nack

IPC: G06T13/40 ,  G06T5/50 ,  G06N3/045

CPC classification number: G06T13/40 ,  G06N3/045 ,  G06T5/50

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure encode features of a source image to obtain a source appearance encoding that represents inherent attributes of a face in the source image; encode features of a target image to obtain a target non-appearance encoding that represents contextual attributes of the target image; combine the source appearance encoding and the target non-appearance encoding to obtain combined image features; and generate a modified target image based on the combined image features, wherein the modified target image includes the inherent attributes of the face in the source image together with the contextual attributes of the target image.

公开(公告)号：US11887216B2

公开(公告)日：2024-01-30

申请号：US17455796

申请日：2021-11-19

Applicant: ADOBE INC.

Inventor： Ratheesh Kalarot ,  Timothy M. Converse ,  Shabnam Ghadar ,  John Thomas Nack ,  Jingwan Lu ,  Elya Shechtman ,  Baldo Faieta ,  Akhilesh Kumar

IPC: G06T5/00 ,  G06T11/00 ,  G06N3/08 ,  G06V40/16

CPC classification number: G06T11/00 ,  G06N3/08 ,  G06V40/168 ,  G06V40/172

Abstract: The present disclosure describes systems and methods for image processing. Embodiments of the present disclosure include an image processing apparatus configured to generate modified images (e.g., synthetic faces) by conditionally changing attributes or landmarks of an input image. A machine learning model of the image processing apparatus encodes the input image to obtain a joint conditional vector that represents attributes and landmarks of the input image in a vector space. The joint conditional vector is then modified, according to the techniques described herein, to form a latent vector used to generate a modified image. In some cases, the machine learning model is trained using a generative adversarial network (GAN) with a normalization technique, followed by joint training of a landmark embedding and attribute embedding (e.g., to reduce inference time).