-
公开(公告)号：US20180357789A1
公开(公告)日：2018-12-13
申请号：US16057161
申请日：2018-08-07
Applicant: Adobe Systems Incorporated
Inventor： Jimei Yang , Yu-Wei Chao , Scott Cohen , Brian Price
CPC classification number: G06T7/74 , G06K9/00369 , G06K9/46 , G06K9/6228 , G06N3/0445 , G06N3/0454 , G06N3/08 , G06T7/246 , G06T7/73 , G06T2207/10016 , G06T2207/20084 , G06T2207/30196
Abstract: A forecasting neural network receives data and extracts features from the data. A recurrent neural network included in the forecasting neural network provides forecasted features based on the extracted features. In an embodiment, the forecasting neural network receives an image, and features of the image are extracted. The recurrent neural network forecasts features based on the extracted features, and pose is forecasted based on the forecasted features. Additionally or alternatively, additional poses are forecasted based on additional forecasted features.
-
公开(公告)号：US20180293738A1
公开(公告)日：2018-10-11
申请号：US15481564
申请日：2017-04-07
Applicant: Adobe Systems Incorporated
Inventor： Jimei Yang , Yu-Wei Chao , Scott Cohen , Brian Price
Abstract: A forecasting neural network receives data and extracts features from the data. A recurrent neural network included in the forecasting neural network provides forecasted features based on the extracted features. In an embodiment, the forecasting neural network receives an image, and features of the image are extracted. The recurrent neural network forecasts features based on the extracted features, and pose is forecasted based on the forecasted features. Additionally or alternatively, additional poses are forecasted based on additional forecasted features.
-
公开(公告)号：US20180268548A1
公开(公告)日：2018-09-20
申请号：US15458887
申请日：2017-03-14
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Zhe Lin , Xin Lu , Xiaohui Shen , Jimei Yang , Chenxi Liu
Abstract: The invention is directed towards segmenting images based on natural language phrases. An image and an n-gram, including a sequence of tokens, are received. An encoding of image features and a sequence of token vectors are generated. A fully convolutional neural network identifies and encodes the image features. A word embedding model generates the token vectors. A recurrent neural network (RNN) iteratively updates a segmentation map based on combinations of the image feature encoding and the token vectors. The segmentation map identifies which pixels are included in an image region referenced by the n-gram. A segmented image is generated based on the segmentation map. The RNN may be a convolutional multimodal RNN. A separate RNN, such as a long short-term memory network, may iteratively update an encoding of semantic features based on the order of tokens. The first RNN may update the segmentation map based on the semantic feature encoding.
-
公开(公告)号：US09972092B2
公开(公告)日：2018-05-15
申请号：US15086590
申请日：2016-03-31
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Yibing Song , Xin Lu , Xiaohui Shen , Jimei Yang
CPC classification number: G06T7/13 , G06K9/00369 , G06K9/38 , G06K9/4628 , G06K9/66 , G06T7/0081 , G06T7/11 , G06T2207/20076 , G06T2207/20081
Abstract: Systems and methods are disclosed for segmenting a digital image to identify an object portrayed in the digital image from background pixels in the digital image. In particular, in one or more embodiments, the disclosed systems and methods use a first neural network and a second neural network to generate image information used to generate a segmentation mask that corresponds to the object portrayed in the digital image. Specifically, in one or more embodiments, the disclosed systems and methods optimize a fit between a mask boundary of the segmentation mask to edges of the object portrayed in the digital image to accurately segment the object within the digital image.
-
Patent Agency Ranking
公开(公告)号：US20170287137A1
公开(公告)日：2017-10-05
申请号：US15086590
申请日：2016-03-31
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Yibing Song , Xin Lu , Xiaohui Shen , Jimei Yang
CPC classification number: G06T7/13 , G06K9/00369 , G06K9/38 , G06K9/4628 , G06K9/66 , G06T7/0081 , G06T7/11 , G06T2207/20076 , G06T2207/20081
Abstract: Systems and methods are disclosed for segmenting a digital image to identify an object portrayed in the digital image from background pixels in the digital image. In particular, in one or more embodiments, the disclosed systems and methods use a first neural network and a second neural network to generate image information used to generate a segmentation mask that corresponds to the object portrayed in the digital image. Specifically, in one or more embodiments, the disclosed systems and methods optimize a fit between a mask boundary of the segmentation mask to edges of the object portrayed in the digital image to accurately segment the object within the digital image.
-
公开(公告)号：US20190035083A1
公开(公告)日：2019-01-31
申请号：US16116609
申请日：2018-08-29
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Xin Lu , Xiaohui Shen , Jimei Yang , Chenxi Liu
CPC classification number: G06T7/11 , G06F17/2715 , G06F17/277 , G06F17/2785 , G06K9/00664 , G06K9/6274 , G06N3/0445 , G06N3/0454 , G06N3/084 , G06T2207/20084 , G06T2207/20101 , G10L15/26
Abstract: The invention is directed towards segmenting images based on natural language phrases. An image and an n-gram, including a sequence of tokens, are received. An encoding of image features and a sequence of token vectors are generated. A fully convolutional neural network identifies and encodes the image features. A word embedding model generates the token vectors. A recurrent neural network (RNN) iteratively updates a segmentation map based on combinations of the image feature encoding and the token vectors. The segmentation map identifies which pixels are included in an image region referenced by the n-gram. A segmented image is generated based on the segmentation map. The RNN may be a convolutional multimodal RNN. A separate RNN, such as a long short-term memory network, may iteratively update an encoding of semantic features based on the order of tokens. The first RNN may update the segmentation map based on the semantic feature encoding.
-
17.发明授权公开(公告)号：US10163003B2
公开(公告)日：2018-12-25
申请号：US15392597
申请日：2016-12-28
Applicant: Adobe Systems Incorporated
Inventor： Zhili Chen , Duygu Ceylan , Byungmoon Kim , Liwen Hu , Jimei Yang
Abstract: Certain embodiments involve recognizing combinations of body shape, pose, and clothing in three-dimensional input images. For example, synthetic training images are generated based on user inputs. These synthetic training images depict different training figures with respective combinations of a body pose, a body shape, and a clothing item. A machine learning algorithm is trained to recognize the pose-shape-clothing combinations in the synthetic training images and to generate feature descriptors describing the pose-shape-clothing combinations. The trained machine learning algorithm is outputted for use by an image manipulation application. In one example, an image manipulation application uses a feature descriptor, which is generated by the machine learning algorithm, to match an input figure in an input image to an example image based on a correspondence between a pose-shape-clothing combination of the input figure and a pose-shape-clothing combination of an example figure in the example image.
-
公开(公告)号：US20180240257A1
公开(公告)日：2018-08-23
申请号：US15438147
申请日：2017-02-21
Applicant: Adobe Systems Incorporated
Inventor： Yijun Li , Chen Fang , Jimei Yang , Zhaowen Wang , Xin Lu
CPC classification number: G06T11/60 , G06K9/46 , G06K9/6256 , G06N3/0454 , G06N3/0472 , G06N3/084 , G06T11/001
Abstract: In some embodiments, techniques for synthesizing an image style based on a plurality of neural networks are described. A computer system selects a style image based on user input that identifies the style image. The computer system generates an image based on a generator neural network and a loss neural network. The generator neural network outputs the synthesized image based on a noise vector and the style image and is trained based on style features generated from the loss neural network. The loss neural network outputs the style features based on a training image. The training image and the style image have a same resolution. The style features are generated at different resolutions of the training image. The computer system provides the synthesized image to a user device in response to the user input.
-
公开(公告)号：US20150206315A1
公开(公告)日：2015-07-23
申请号：US14159658
申请日：2014-01-21
Applicant: Adobe Systems Incorporated
Inventor： Brian L. Price , Scott Cohen , Jimei Yang
IPC: G06T7/00
CPC classification number: G06T7/0081 , G06T7/11 , G06T7/143 , G06T7/162 , G06T2207/10024 , G06T2207/20016 , G06T2207/20081
Abstract: Disclosed are various embodiments labeling objects using multi-scale partitioning, rare class expansion, and/or spatial context techniques. An input image may be partitioned using different scale values to produce a different set of superpixels for each of the different scale values. Potential object labels for superpixels in each different set of superpixels of the input image may be assessed by comparing descriptors of the superpixels in each different set of superpixels of the input image with descriptors of reference superpixels in labeled reference images. An object label may then be assigned for a pixel of the input image based at least in part on the assessing of the potential object labels.
Abstract translation: 公开了使用多尺度分割，稀有类扩展和/或空间上下文技术标记对象的各种实施例。 可以使用不同的比例值对输入图像进行分区，以针对不同比例值中的每一者产生不同的超像素组。 可以通过将输入图像的每个不同的超像素集合中的超像素的描述符与标记的参考图像中的参考超像素的描述符进行比较来评估输入图像的每个不同的超像素集合中的超像素的潜在对象标签。 至少部分地基于对潜在对象标签的评估，可以为输入图像的像素分配对象标签。
-
-
-
-
-
-
-
-
Search Results
19
records
(took 0.017 seconds)
