-
Patent Agency Ranking
公开(公告)号：US20230289970A1
公开(公告)日：2023-09-14
申请号：US17693618
申请日：2022-03-14
Applicant: Adobe Inc.
Inventor： Gaurav Parmar , Krishna Kumar Singh , Yijun Li , Richard Zhang , Jingwan Lu
CPC classification number: G06T7/11 , G06T11/001 , G06T3/4046 , G06T2207/20084 , G06T2207/20081
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.
-
公开(公告)号：US12159413B2
公开(公告)日：2024-12-03
申请号：US17693618
申请日：2022-03-14
Applicant: Adobe Inc.
Inventor： Gaurav Parmar , Krishna Kumar Singh , Yijun Li , Richard Zhang , Jingwan Lu
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.
-
公开(公告)号：US20240338799A1
公开(公告)日：2024-10-10
申请号：US18178212
申请日：2023-03-03
Applicant: Adobe Inc.
Inventor： Yijun Li , Richard Zhang , Krishna Kumar Singh , Jingwan Lu , Gaurav Parmar , Jun-Yan Zhu
IPC: G06T5/00 , G06F40/126 , G06T5/50
CPC classification number: G06T5/70 , G06F40/126 , G06T5/50 , G06T2207/20081 , G06T2207/20084
Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing machine learning models to generate modified digital images. In particular, in some embodiments, the disclosed systems generate image editing directions between textual identifiers of two visual features utilizing a language prediction machine learning model and a text encoder. In some embodiments, the disclosed systems generated an inversion of a digital image utilizing a regularized inversion model to guide forward diffusion of the digital image. In some embodiments, the disclosed systems utilize cross-attention guidance to preserve structural details of a source digital image when generating a modified digital image with a diffusion neural network.
-
4.发明公开公开(公告)号：US20240331236A1
公开(公告)日：2024-10-03
申请号：US18178194
申请日：2023-03-03
Applicant: Adobe Inc.
Inventor： Yijun Li , Richard Zhang , Krishna Kumar Singh , Jingwan Lu , Gaurav Parmar , Jun-Yan Zhu
CPC classification number: G06T11/60 , G06T5/70 , G06T9/00 , G06V10/761 , G06V10/82 , G06V20/70 , G06T2207/20182
Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing machine learning models to generate modified digital images. In particular, in some embodiments, the disclosed systems generate image editing directions between textual identifiers of two visual features utilizing a language prediction machine learning model and a text encoder. In some embodiments, the disclosed systems generated an inversion of a digital image utilizing a regularized inversion model to guide forward diffusion of the digital image. In some embodiments, the disclosed systems utilize cross-attention guidance to preserve structural details of a source digital image when generating a modified digital image with a diffusion neural network.
-
5.发明公开公开(公告)号：US20240296607A1
公开(公告)日：2024-09-05
申请号：US18178167
申请日：2023-03-03
Applicant: Adobe Inc.
Inventor： Yijun Li , Richard Zhang , Krishna Kumar Singh , Jingwan Lu , Gaurav Parmar , Jun-Yan Zhu
CPC classification number: G06T11/60 , G06F40/56 , G06T1/0021 , G06T5/70 , G06V10/44 , G06V10/82 , G06V20/70 , G06T2207/20182
Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing machine learning models to generate modified digital images. In particular, in some embodiments, the disclosed systems generate image editing directions between textual identifiers of two visual features utilizing a language prediction machine learning model and a text encoder. In some embodiments, the disclosed systems generated an inversion of a digital image utilizing a regularized inversion model to guide forward diffusion of the digital image. In some embodiments, the disclosed systems utilize cross-attention guidance to preserve structural details of a source digital image when generating a modified digital image with a diffusion neural network.
-
-
-
-
Search Results
5
records
(took 0.015 seconds)
