公开(公告)号：US20200242774A1

公开(公告)日：2020-07-30

申请号：US16721852

申请日：2019-12-19

Applicant: Nvidia Corporation

Inventor： Taesung Park ,  Ming-Yu Liu ,  Ting-Chun Wang ,  Junyan Zhu

IPC: G06T7/11 ,  G06N3/08 ,  G06N20/10 ,  G06N3/04

Abstract: A user can create a basic semantic layout that includes two or more regions identified by the user, each region being associated with a semantic label indicating a type of object(s) to be rendered in that region. The semantic layout can be provided as input to an image synthesis network. The network can be a trained machine learning network, such as a generative adversarial network (GAN), that includes a conditional, spatially-adaptive normalization layer for propagating semantic information from the semantic layout to other layers of the network. The synthesis can involve both normalization and de-normalization, where each region of the layout can utilize different normalization parameter values. An image is inferred from the network, and rendered for display to the user. The user can change labels or regions in order to cause a new or updated image to be generated.

公开(公告)号：US20200242771A1

公开(公告)日：2020-07-30

申请号：US16258322

申请日：2019-01-25

Applicant: Nvidia Corporation

Inventor： Taesung Park ,  Ming-Yu Liu ,  Ting-Chun Wang ,  Junyan Zhu

IPC: G06T7/11 ,  G06N3/04 ,  G06N3/08 ,  G06N20/10

Abstract: A user can create a basic semantic layout that includes two or more regions identified by the user, each region being associated with a semantic label indicating a type of object(s) to be rendered in that region. The semantic layout can be provided as input to an image synthesis network. The network can be a trained machine learning network, such as a generative adversarial network (GAN), that includes a conditional, spatially-adaptive normalization layer for propagating semantic information from the semantic layout to other layers of the network. The synthesis can involve both normalization and de-normalization, where each region of the layout can utilize different normalization parameter values. An image is inferred from the network, and rendered for display to the user. The user can change labels or regions in order to cause a new or updated image to be generated.