Invention Grant
- Patent Title: Attribute conditioned image generation
-
Application No.: US16934858Application Date: 2020-07-21
-
Publication No.: US11640684B2Publication Date: 2023-05-02
- Inventor: Rameen Abdal , Peter Wonka , Niloy Mitra , Peihao Zhu
- Applicant: ADOBE INC. , KING ABDULLAH UNIVERSITY OF SCIENCE AND TECHNOLOGY
- Applicant Address: US CA San Jose; SA Thuwal
- Assignee: ADOBE INC.,KING ABDULLAH UNIVERSITY OF SCIENCE AND TECHNOLOGY
- Current Assignee: ADOBE INC.,KING ABDULLAH UNIVERSITY OF SCIENCE AND TECHNOLOGY
- Current Assignee Address: US CA San Jose; SA Thuwal
- Agency: F. Chau & Associates, LLC
- Main IPC: G06T11/60
- IPC: G06T11/60 ; G06V40/16

Abstract:
A method, apparatus, and non-transitory computer readable medium for image processing are described. Embodiments of the method, apparatus, and non-transitory computer readable medium include identifying an original image including a plurality of semantic attributes, wherein each of the semantic attributes represents a complex set of features of the original image; identifying a target attribute value that indicates a change to a target attribute of the semantic attributes; computing a modified feature vector based on the target attribute value, wherein the modified feature vector incorporates the change to the target attribute while holding at least one preserved attribute of the semantic attributes substantially unchanged; and generating a modified image based on the modified feature vector, wherein the modified image includes the change to the target attribute and retains the at least one preserved attribute from the original image.
Public/Granted literature
- US20220028139A1 ATTRIBUTE CONDITIONED IMAGE GENERATION Public/Granted day:2022-01-27
Information query