-
1.发明申请公开(公告)号：US20220414431A1
公开(公告)日：2022-12-29
申请号：US17899936
申请日：2022-08-31
Applicant: Adobe Inc.
Inventor： Richard Zhang , Sylvain Philippe Paris , Junyan Zhu , Aaron Phillip Hertzmann , Jacob Minyoung Huh
Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.
-
公开(公告)号：US20190108203A1
公开(公告)日：2019-04-11
申请号：US15729855
申请日：2017-10-11
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Hailin Jin , Aaron Phillip Hertzmann , Shuhui Jiang
Abstract: The present disclosure relates to an asymmetric font pairing system that efficiently pairs digital fonts. For example, in one or more embodiments, the asymmetric font pairing system automatically identifies and provides users with visually aesthetic font pairs for use in different sections of an electronic document. In particular, the asymmetric font pairing system learns visually aesthetic font pairs using joint symmetric and asymmetric compatibility metric learning. In addition, the asymmetric font pairing system provides compact compatibility spaces (e.g., a symmetric compatibility space and an asymmetric compatibility space) to computing devices (e.g., client devices and server devices), which enable the computing devices to quickly and efficiently provide font pairs to users.
-
公开(公告)号：US10235897B2
公开(公告)日：2019-03-19
申请号：US15294123
申请日：2016-10-14
Applicant: Adobe Inc.
Inventor： Holger Winnemoeller , Jun Xie , Wilmot Wei-Mau Li , Aaron Phillip Hertzmann
Abstract: Methods for providing drawing assistance to a user sketching an image include geometrically correcting adjusting user strokes to improve their placement and appearance. In particular, one or more guidance maps indicate where the user “should” draw lines. As a user draws a stroke, the stroke is geometrically corrected by moving the stroke toward a portion of the guidance maps corresponding to the feature of the image the user is intending to draw based feature labels. To further improve the user drawn lines, parametric adjustments are optionally made to the geometrically-corrected stroke to emphasize “correctly” drawn lines and de-emphasize “incorrectly” drawn lines.
-
公开(公告)号：US12165034B2
公开(公告)日：2024-12-10
申请号：US18301887
申请日：2023-04-17
Applicant: Adobe Inc.
Abstract: A generative neural network control system controls a generative neural network by modifying the intermediate latent space in the generative neural network. The generative neural network includes multiple layers each generating a set of activation values. An initial layer (and optionally additional layers) receives an input latent vector, and a final layer outputs an image generated based on the input latent vector. The data that is input to each layer (other than the initial layer) is referred to as data in an intermediate latent space. The data in the intermediate latent space includes activation values (e.g., generated by the previous layer or modified using various techniques) and optionally a latent vector. The generative neural network control system modifies the intermediate latent space to achieve various different effects when generating a new image.
-
公开(公告)号：US11003831B2
公开(公告)日：2021-05-11
申请号：US15729855
申请日：2017-10-11
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Hailin Jin , Aaron Phillip Hertzmann , Shuhui Jiang
IPC: G06F40/109 , G06N3/04 , G06K9/62 , G06F9/451 , G06N3/08
Abstract: The present disclosure relates to an asymmetric font pairing system that efficiently pairs digital fonts. For example, in one or more embodiments, the asymmetric font pairing system automatically identifies and provides users with visually aesthetic font pairs for use in different sections of an electronic document. In particular, the asymmetric font pairing system learns visually aesthetic font pairs using joint symmetric and asymmetric compatibility metric learning. In addition, the asymmetric font pairing system provides compact compatibility spaces (e.g., a symmetric compatibility space and an asymmetric compatibility space) to computing devices (e.g., client devices and server devices), which enable the computing devices to quickly and efficiently provide font pairs to users.
-
Patent Agency Ranking
公开(公告)号：US20230342592A1
公开(公告)日：2023-10-26
申请号：US18301887
申请日：2023-04-17
Applicant: Adobe Inc.
Abstract: A generative neural network control system controls a generative neural network by modifying the intermediate latent space in the generative neural network. The generative neural network includes multiple layers each generating a set of activation values. An initial layer (and optionally additional layers) receives an input latent vector, and a final layer outputs an image generated based on the input latent vector. The data that is input to each layer (other than the initial layer) is referred to as data in an intermediate latent space. The data in the intermediate latent space includes activation values (e.g., generated by the previous layer or modified using various techniques) and optionally a latent vector. The generative neural network control system modifies the intermediate latent space to achieve various different effects when generating a new image.
-
公开(公告)号：US11657255B2
公开(公告)日：2023-05-23
申请号：US16798263
申请日：2020-02-21
Applicant: Adobe Inc.
CPC classification number: G06N3/0454 , G06N3/08
Abstract: A generative neural network control system controls a generative neural network by modifying the intermediate latent space in the generative neural network. The generative neural network includes multiple layers each generating a set of activation values. An initial layer (and optionally additional layers) receives an input latent vector, and a final layer outputs an image generated based on the input latent vector. The data that is input to each layer (other than the initial layer) is referred to as data in an intermediate latent space. The data in the intermediate latent space includes activation values (e.g., generated by the previous layer or modified using various techniques) and optionally a latent vector. The generative neural network control system modifies the intermediate latent space to achieve various different effects when generating a new image.
-
8.发明申请公开(公告)号：US20210264235A1
公开(公告)日：2021-08-26
申请号：US16798271
申请日：2020-02-21
Applicant: Adobe Inc.
Inventor： Richard Zhang , Sylvain Philippe Paris , Junyan Zhu , Aaron Phillip Hertzmann , Jacob Minyoung Huh
Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.
-
公开(公告)号：US20210264234A1
公开(公告)日：2021-08-26
申请号：US16798263
申请日：2020-02-21
Applicant: Adobe Inc.
Abstract: A generative neural network control system controls a generative neural network by modifying the intermediate latent space in the generative neural network. The generative neural network includes multiple layers each generating a set of activation values. An initial layer (and optionally additional layers) receives an input latent vector, and a final layer outputs an image generated based on the input latent vector. The data that is input to each layer (other than the initial layer) is referred to as data in an intermediate latent space. The data in the intermediate latent space includes activation values (e.g., generated by the previous layer or modified using various techniques) and optionally a latent vector. The generative neural network control system modifies the intermediate latent space to achieve various different effects when generating a new image.
-
10.发明授权公开(公告)号：US11615292B2
公开(公告)日：2023-03-28
申请号：US17899936
申请日：2022-08-31
Applicant: Adobe Inc.
Inventor： Richard Zhang , Sylvain Philippe Paris , Junyan Zhu , Aaron Phillip Hertzmann , Jacob Minyoung Huh
Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.
-
-
-
-
-
-
-
-
-
Search Results
18
records
(took 0.015 seconds)
