Invention Grant
- Patent Title: Image inversion using multiple latent spaces
-
Application No.: US17693618Application Date: 2022-03-14
-
Publication No.: US12159413B2Publication Date: 2024-12-03
- Inventor: Gaurav Parmar , Krishna Kumar Singh , Yijun Li , Richard Zhang , Jingwan Lu
- Applicant: Adobe Inc.
- Applicant Address: US CA San Jose
- Assignee: Adobe Inc.
- Current Assignee: Adobe Inc.
- Current Assignee Address: US CA San Jose
- Agency: FIG. 1 Patents
- Main IPC: G06T7/11
- IPC: G06T7/11 ; G06T3/4046 ; G06T11/00

Abstract:
In implementations of systems for image inversion using multiple latent spaces, a computing device implements an inversion system to generate a segment map that segments an input digital image into a first image region and a second image region and assigns the first image region to a first latent space and the second image region to a second latent space that corresponds to a layer of a convolutional neural network. An inverted latent representation of the input digital image is computed using a binary mask for the second image region. The inversion system modifies the inverted latent representation of the input digital image using an edit direction vector that corresponds to a visual feature. An output digital image is generated that depicts a reconstruction of the input digital image having the visual feature based on the modified inverted latent representation of the input digital image.
Public/Granted literature
- US20230289970A1 Image Inversion Using Multiple Latent Spaces Public/Granted day:2023-09-14
Information query