公开(公告)号：US20200311986A1

公开(公告)日：2020-10-01

申请号：US16366393

申请日：2019-03-27

Applicant: GM Global Technology Operations LLC

Inventor： Wei Tong ,  Chengqi Bian ,  Farui Peng ,  Shuqing Zeng

IPC: G06T11/00 ,  G06T5/00 ,  G06T5/50 ,  G06N3/08 ,  G06N3/04 ,  G06N20/20 ,  B60R11/04

Abstract: A method for image style transfer using a Semantic Preserved Generative Adversarial Network (SPGAN) includes: receiving a source image; inputting the source image into the SPGAN; extracting a source-semantic feature data from the source image; generating, by the first decoder, a first synthetic image including the source semantic content of the source image in a target style of a target image using the source-semantic feature data extracted by the first encoder of the first generator network, wherein the first synthetic image includes first-synthetic feature data; determining a first encoder loss using the source-semantic feature data and the first-synthetic feature data; discriminating the first synthetic image against the target image to determine a GAN loss; determining a total loss as a function of the first encoder loss and the first GAN loss; and training the first generator network and the first discriminator network.

公开(公告)号：US10832450B2

公开(公告)日：2020-11-10

申请号：US16366393

申请日：2019-03-27

Applicant: GM Global Technology Operations LLC

Inventor： Wei Tong ,  Chengqi Bian ,  Farui Peng ,  Shuqing Zeng

IPC: G06T11/00 ,  B60R11/04 ,  G06T5/00 ,  G06T5/50 ,  G06N20/20 ,  G06N3/04 ,  G06N3/08

Abstract: A method for image style transfer using a Semantic Preserved Generative Adversarial Network (SPGAN) includes: receiving a source image; inputting the source image into the SPGAN; extracting a source-semantic feature data from the source image; generating, by the first decoder, a first synthetic image including the source semantic content of the source image in a target style of a target image using the source-semantic feature data extracted by the first encoder of the first generator network, wherein the first synthetic image includes first-synthetic feature data; determining a first encoder loss using the source-semantic feature data and the first-synthetic feature data; discriminating the first synthetic image against the target image to determine a GAN loss; determining a total loss as a function of the first encoder loss and the first GAN loss; and training the first generator network and the first discriminator network.