Invention Grant
- Patent Title: Semantically-consistent image style transfer
-
Application No.: US16759689Application Date: 2018-10-29
-
Publication No.: US11380034B2Publication Date: 2022-07-05
- Inventor: Stephan Gouws , Frederick Bertsch , Konstantinos Bousmalis , Amelie Royer , Kevin Patrick Murphy
- Applicant: GOOGLE LLC
- Applicant Address: US CA Mountain View
- Assignee: GOOGLE LLC
- Current Assignee: GOOGLE LLC
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Priority: GR20170100484 20171027
- International Application: PCT/US2018/058044 WO 20181029
- International Announcement: WO2019/084562 WO 20190502
- Main IPC: G06T11/60
- 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.
Public/Granted literature
- US20200342643A1 SEMANTICALLY-CONSISTENT IMAGE STYLE TRANSFER Public/Granted day:2020-10-29
Information query