公开(公告)号：US20200342643A1

公开(公告)日：2020-10-29

申请号：US16759689

申请日：2018-10-29

Applicant: GOOGLE LLC

Inventor： Stephan Gouws ,  Frederick Bertsch ,  Konstantinos Bousmalis ,  Amelie Royer ,  Kevin Patrick Murphy

IPC: G06T11/60 ,  G06F16/55 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for semantically-consistent image style transfer. One of the methods includes: receiving an input source domain image; processing the source domain image using one or more source domain low-level encoder neural network layers to generate a low-level representation; processing the low-level representation using one more high-level encoder neural network layers to generate an embedding of the input source domain image; processing the embedding using one or more high-level decoder neural network layers to generate a high-level feature representation of features of the input source domain image; and processing the high-level feature representation of the features of the input source domain image using one or more target domain low-level decoder neural network layers to generate an output target domain image that is from the target domain but that has similar semantics to the input source domain image.

公开(公告)号：US11380034B2

公开(公告)日：2022-07-05

申请号：US16759689

申请日：2018-10-29

Applicant: GOOGLE LLC

Inventor： Stephan Gouws ,  Frederick Bertsch ,  Konstantinos Bousmalis ,  Amelie Royer ,  Kevin Patrick Murphy

IPC: G06T11/60 ,  G06F16/55 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for semantically-consistent image style transfer. One of the methods includes: receiving an input source domain image; processing the source domain image using one or more source domain low-level encoder neural network layers to generate a low-level representation; processing the low-level representation using one more high-level encoder neural network layers to generate an embedding of the input source domain image; processing the embedding using one or more high-level decoder neural network layers to generate a high-level feature representation of features of the input source domain image; and processing the high-level feature representation of the features of the input source domain image using one or more target domain low-level decoder neural network layers to generate an output target domain image that is from the target domain but that has similar semantics to the input source domain image.