-
公开(公告)号：US10997463B2
公开(公告)日：2021-05-04
申请号：US16184779
申请日：2018-11-08
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Hailin Jin , Yang Liu
Abstract: In implementations of recognizing text in images, text recognition systems are trained using noisy images that have nuisance factors applied, and corresponding clean images (e.g., without nuisance factors). Clean images serve as supervision at both feature and pixel levels, so that text recognition systems are trained to be feature invariant (e.g., by requiring features extracted from a noisy image to match features extracted from a clean image), and feature complete (e.g., by requiring that features extracted from a noisy image be sufficient to generate a clean image). Accordingly, text recognition systems generalize to text not included in training images, and are robust to nuisance factors. Furthermore, since clean images are provided as supervision at feature and pixel levels, training requires fewer training images than text recognition systems that are not trained with a supervisory clean image, thus saving time and resources.
-
72.发明申请公开(公告)号：US20200349688A1
公开(公告)日：2020-11-05
申请号：US16930736
申请日：2020-07-16
Applicant: Adobe Inc.
Inventor： Chen Fang , Zhe Lin , Zhaowen Wang , Yulun Zhang , Yilin Wang , Jimei Yang
Abstract: A style of a digital image is transferred to another digital image of arbitrary resolution. A high-resolution (HR) content image is segmented into several low-resolution (LR) patches. The resolution of a style image is matched to have the same resolution as the LR content image patches. Style transfer is then performed on a patch-by-patch basis using, for example, a pair of feature transforms—whitening and coloring. The patch-by-patch style transfer process is then repeated at several increasing resolutions, or scale levels, of both the content and style images. The results of the style transfer at each scale level are incorporated into successive scale levels up to and including the original HR scale. As a result, style transfer can be performed with images having arbitrary resolutions to produce visually pleasing results with good spatial consistency.
-
73.发明申请公开(公告)号：US20200258204A1
公开(公告)日：2020-08-13
申请号：US16271058
申请日：2019-02-08
Applicant: Adobe Inc.
Inventor： Chen Fang , Zhe Lin , Zhaowen Wang , Yulun Zhang , Yilin Wang , Jimei Yang
Abstract: A style of a digital image is transferred to another digital image of arbitrary resolution. A high-resolution (HR) content image is segmented into several low-resolution (LR) patches. The resolution of a style image is matched to have the same resolution as the LR content image patches. Style transfer is then performed on a patch-by-patch basis using, for example, a pair of feature transforms—whitening and coloring. The patch-by-patch style transfer process is then repeated at several increasing resolutions, or scale levels, of both the content and style images. The results of the style transfer at each scale level are incorporated into successive scale levels up to and including the original HR scale. As a result, style transfer can be performed with images having arbitrary resolutions to produce visually pleasing results with good spatial consistency.
-
公开(公告)号：US10699166B2
公开(公告)日：2020-06-30
申请号：US15853120
申请日：2017-12-22
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Luoqi Liu , Hailin Jin
Abstract: Font recognition and similarity determination techniques and systems are described. In a first example, localization techniques are described to train a model using machine learning (e.g., a convolutional neural network) using training images. The model is then used to localize text in a subsequently received image, and may do so automatically and without user intervention, e.g., without specifying any of the edges of a bounding box. In a second example, a deep neural network is directly learned as an embedding function of a model that is usable to determine font similarity. In a third example, techniques are described that leverage attributes described in metadata associated with fonts as part of font recognition and similarity determinations.
-
公开(公告)号：US10528649B2
公开(公告)日：2020-01-07
申请号：US15280505
申请日：2016-09-29
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Hailin Jin
IPC: G06F17/21
Abstract: Font recognition and similarity determination techniques and systems are described. For example, a computing device receives an image including a font and extracts font features corresponding to the font. The computing device computes font feature distances between the font and fonts from a set of training fonts. The computing device calculates, based on the font feature distances, similarity scores for the font and the training fonts used for calculating features distances. The computing device determines, based on the similarity scores, final similarity scores for the font relative to the training fonts.
-
Patent Agency Ranking
公开(公告)号：US10430661B2
公开(公告)日：2019-10-01
申请号：US15384831
申请日：2016-12-20
Applicant: Adobe Inc.
Inventor： Hao Hu , Zhaowen Wang , Joon-Young Lee , Zhe Lin
Abstract: Techniques and systems are described to generate a compact video feature representation for sequences of frames in a video. In one example, values of features are extracted from each frame of a plurality of frames of a video using machine learning, e.g., through use of a convolutional neural network. A video feature representation is generated of temporal order dynamics of the video, e.g., through use of a recurrent neural network. For example, a maximum value is maintained of each feature of the plurality of features that has been reached for the plurality of frames in the video. A timestamp is also maintained as indicative of when the maximum value is reached for each feature of the plurality of features. The video feature representation is then output as a basis to determine similarity of the video with at least one other video based on the video feature representation.
-
公开(公告)号：US20190251612A1
公开(公告)日：2019-08-15
申请号：US15897856
申请日：2018-02-15
Applicant: Adobe Inc. , The Regents of the University of California
Inventor： Chen Fang , Zhaowen Wang , Wangcheng Kang , Julian McAuley
CPC classification number: G06Q30/0621 , G06F16/532 , G06N3/08
Abstract: The present disclosure relates to a personalized fashion generation system that synthesizes user-customized images using deep learning techniques based on visually-aware user preferences. In particular, the personalized fashion generation system employs an image generative adversarial neural network and a personalized preference network to synthesize new fashion items that are individually customized for a user. Additionally, the personalized fashion generation system can modify existing fashion items to tailor the fashion items to a user's tastes and preferences.
-
公开(公告)号：US20190147627A1
公开(公告)日：2019-05-16
申请号：US15814751
申请日：2017-11-16
Applicant: Adobe Inc.
Inventor： Zhili Chen , Zhaowen Wang , Rundong Wu , Jimei Yang
CPC classification number: G06T11/001 , G06N3/0454 , G06N3/08 , G06T9/002 , G06T11/203 , G06T11/40
Abstract: Oil painting simulation techniques are disclosed which simulate painting brush strokes using a trained neural network. In some examples, a method may include inferring a new height map of existing paint on a canvas after a new painting brush stroke is applied based on a bristle trajectory map that represents the new painting brush stroke and a height map of existing paint on the canvas prior to the application of the new painting brush stroke, and generating a rendering of the new painting brush stroke based on the new height map of existing paint on the canvas after the new painting brush stroke is applied to the canvas and a color map.
-
公开(公告)号：US10192321B2
公开(公告)日：2019-01-29
申请号：US15409321
申请日：2017-01-18
Applicant: ADOBE INC.
Inventor： Chen Fang , Zhaowen Wang , Yijun Li , Jimei Yang
IPC: G06T15/04 , G06T7/40 , G06T11/00 , G06T5/50 , G06F3/0482
Abstract: Systems and techniques that synthesize an image with similar texture to a selected style image. A generator network is trained to synthesize texture images depending on a selection unit input. The training configures the generator network to synthesize texture images that are similar to individual style images of multiple style images based on which is selected by the selection unit input. The generator network can be configured to minimize a covariance matrix-based style loss and/or a diversity loss in synthesizing the texture images. After training the generator network, the generator network is used to synthesize texture images for selected style images. For example, this can involve receiving user input selecting a selected style image, determining the selection unit input based on the selected style image, and synthesizing texture images using the generator network with the selection unit input and noise input.
-
公开(公告)号：US12105767B2
公开(公告)日：2024-10-01
申请号：US17735748
申请日：2022-05-03
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Yue Bai , John Philip Collomosse
IPC: G06F16/9537 , G06F40/103 , G06F40/30 , G06V30/19 , G06K15/02 , G06N3/08 , G06N20/00 , G06V10/82 , G06V30/412 , G06V30/414
CPC classification number: G06F16/9537 , G06F40/103 , G06F40/30 , G06V30/19127 , G06K15/1885 , G06N3/08 , G06N20/00 , G06V10/82 , G06V30/412 , G06V30/414
Abstract: Digital content layout encoding techniques for search are described. In these techniques, a layout representation is generated (using machine learning automatically and without user intervention) that describes a layout of elements included within the digital content. In an implementation, the layout representation includes a description of both spatial and structural aspects of the elements in relation to each other. To do so, a two-pathway pipeline that is configured to model layout from both spatial and structural aspects using a spatial pathway, and a structural pathway, respectively. In one example, this is also performed through use of multi-level encoding and fusion to generate a layout representation.
-
-
-
-
-
-
-
-
-
Search Results
104
records
(took 0.019 seconds)
