公开(公告)号：US12217395B2

公开(公告)日：2025-02-04

申请号：US17660968

申请日：2022-04-27

Applicant: ADOBE INC.

Inventor： Sangryul Jeon ,  Zhifei Zhang ,  Zhe Lin ,  Scott Cohen ,  Zhihong Ding

IPC: G06V10/774 ,  G06T5/50 ,  G06V10/40 ,  G06V10/44 ,  G06V10/75 ,  G06V10/77

Abstract: Systems and methods for image processing are configured. Embodiments of the present disclosure encode a content image and a style image using a machine learning model to obtain content features and style features, wherein the content image includes a first object having a first appearance attribute and the style image includes a second object having a second appearance attribute; align the content features and the style features to obtain a sparse correspondence map that indicates a correspondence between a sparse set of pixels of the content image and corresponding pixels of the style image; and generate a hybrid image based on the sparse correspondence map, wherein the hybrid image depicts the first object having the second appearance attribute.

公开(公告)号：US20230351566A1

公开(公告)日：2023-11-02

申请号：US17660968

申请日：2022-04-27

Applicant: ADOBE INC.

Inventor： Sangryul Jeon ,  Zhifei Zhang ,  Zhe Lin ,  Scott Cohen ,  Zhihong Ding

IPC: G06T5/50 ,  G06V10/40 ,  G06V10/75 ,  G06V10/77 ,  G06V10/774 ,  G06V10/44

CPC classification number: G06T5/50 ,  G06V10/513 ,  G06V10/751 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/454 ,  G06T2207/20221 ,  G06T2207/20081

Abstract: Systems and methods for image processing are configured. Embodiments of the present disclosure encode a content image and a style image using a machine learning model to obtain content features and style features, wherein the content image includes a first object having a first appearance attribute and the style image includes a second object having a second appearance attribute; align the content features and the style features to obtain a sparse correspondence map that indicates a correspondence between a sparse set of pixels of the content image and corresponding pixels of the style image; and generate a hybrid image based on the sparse correspondence map, wherein the hybrid image depicts the first object having the second appearance attribute.