公开(公告)号：US10482609B2

公开(公告)日：2019-11-19

申请号：US15478784

申请日：2017-04-04

Applicant: General Electric Company

Inventor： Ser Nam Lim ,  Mustafa Devrim Kaba ,  Mustafa Uzunbas ,  David Diwinsky

IPC: G06T7/215 ,  G06N3/04 ,  G06N3/08 ,  G06T7/277

Abstract: A generative adversarial network (GAN) system includes a generator sub-network configured to examine images of an object moving relative to a viewer of the object. The generator sub-network also is configured to generate one or more distribution-based images based on the images that were examined. The system also includes a discriminator sub-network configured to examine the one or more distribution-based images to determine whether the one or more distribution-based images accurately represent the object. A predicted optical flow of the object is represented by relative movement of the object as shown in the one or more distribution-based images.

公开(公告)号：US20180286055A1

公开(公告)日：2018-10-04

申请号：US15478784

申请日：2017-04-04

Applicant: General Electric Company

Inventor： Ser Nam Lim ,  Mustafa Devrim Kaba ,  Mustafa Uzunbas ,  David Diwinsky

IPC: G06T7/215

CPC classification number: G06T7/215 ,  G06N3/0454 ,  G06N3/084 ,  G06T7/277 ,  G06T2207/20084

Abstract: A generative adversarial network (GAN) system includes a generator sub-network configured to examine images of an object moving relative to a viewer of the object. The generator sub-network also is configured to generate one or more distribution-based images based on the images that were examined. The system also includes a discriminator sub-network configured to examine the one or more distribution-based images to determine whether the one or more distribution-based images accurately represent the object. A predicted optical flow of the object is represented by relative movement of the object as shown in the one or more distribution-based images.