-
公开(公告)号：US10089742B1
公开(公告)日：2018-10-02
申请号：US15458887
申请日：2017-03-14
发明人： Zhe Lin , Xin Lu , Xiaohui Shen , Jimei Yang , Chenxi Liu
摘要： 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：US09607391B2
公开(公告)日：2017-03-28
申请号：US14817731
申请日：2015-08-04
发明人： Brian Price , Zhe Lin , Scott Cohen , Jimei Yang
CPC分类号： G06T7/251 , G06K9/6215 , G06T7/11 , G06T7/174 , G06T2207/10024 , G06T2207/20076 , G06T2207/20081
摘要： Systems and methods are disclosed herein for using one or more computing devices to automatically segment an object in an image by referencing a dataset of already-segmented images. The technique generally involves identifying a patch of an already-segmented image in the dataset based on the patch of the already-segmented image being similar to an area of the image including a patch of the image. The technique further involves identifying a mask of the patch of the already-segmented image, the mask representing a segmentation in the already-segmented image. The technique also involves segmenting the object in the image based on at least a portion of the mask of the patch of the already-segmented image.
-
公开(公告)号：US20170039723A1
公开(公告)日：2017-02-09
申请号：US14817731
申请日：2015-08-04
发明人： Brian Price , Zhe Lin , Scott Cohen , Jimei Yang
CPC分类号： G06T7/251 , G06K9/6215 , G06T7/11 , G06T7/174 , G06T2207/10024 , G06T2207/20076 , G06T2207/20081
摘要： Systems and methods are disclosed herein for using one or more computing devices to automatically segment an object in an image by referencing a dataset of already-segmented images. The technique generally involves identifying a patch of an already-segmented image in the dataset based on the patch of the already-segmented image being similar to an area of the image including a patch of the image. The technique further involves identifying a mask of the patch of the already-segmented image, the mask representing a segmentation in the already-segmented image. The technique also involves segmenting the object in the image based on at least a portion of the mask of the patch of the already-segmented image.
摘要翻译： 本文公开的系统和方法用于使用一个或多个计算设备通过参考已经分割的图像的数据集自动地分割图像中的对象。 该技术通常涉及基于已经分段的图像的片段类似于包括图像的片段的图像的区域来识别数据集中的已经分割的图像的片段。 该技术还涉及识别已经分割的图像的斑块的掩模，该掩码表示已经分割的图像中的分割。 该技术还涉及基于已经分割的图像的补片的掩模的至少一部分来分割图像中的对象。
-
公开(公告)号：US20180253869A1
公开(公告)日：2018-09-06
申请号：US15448206
申请日：2017-03-02
发明人： Mehmet Yumer , Jimei Yang , Guilin Liu , Duygu Ceylan Aksit
CPC分类号： G06T11/001 , G06F17/50 , G06N3/0454 , G06N3/082 , G06T11/60
摘要： The present disclosure includes methods and systems for generating modified digital images utilizing a neural network that includes a rendering layer. In particular, the disclosed systems and methods can train a neural network to decompose an input digital image into intrinsic physical properties (e.g., such as material, illumination, and shape). Moreover, the systems and methods can substitute one of the intrinsic physical properties for a target property (e.g., a modified material, illumination, or shape). The systems and methods can utilize a rendering layer trained to synthesize a digital image to generate a modified digital image based on the target property and the remaining (unsubstituted) intrinsic physical properties. Systems and methods can increase the accuracy of modified digital images by generating modified digital images that realistically reflect a confluence of intrinsic physical properties of an input digital image and target (i.e., modified) properties.
-
公开(公告)号：US09396546B2
公开(公告)日：2016-07-19
申请号：US14159658
申请日：2014-01-21
发明人： Brian L. Price , Scott Cohen , Jimei Yang
CPC分类号： G06T7/0081 , G06T7/11 , G06T7/143 , G06T7/162 , G06T2207/10024 , G06T2207/20016 , G06T2207/20081
摘要： 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.
摘要翻译： 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。
-
公开(公告)号：US20190114818A1
公开(公告)日：2019-04-18
申请号：US15785386
申请日：2017-10-16
发明人： Zhe Lin , Xin Lu , Xiaohui Shen , Jimei Yang , Jiahui Yu
摘要： Predicting patch displacement maps using a neural network is described. Initially, a digital image on which an image editing operation is to be performed is provided as input to a patch matcher having an offset prediction neural network. From this image and based on the image editing operation for which this network is trained, the offset prediction neural network generates an offset prediction formed as a displacement map, which has offset vectors that represent a displacement of pixels of the digital image to different locations for performing the image editing operation. Pixel values of the digital image are copied to the image pixels affected by the operation by: determining the vectors pixels that correspond to the image pixels affected by the image editing operation and mapping the pixel values of the image pixels represented by the determined offset vectors to the affected pixels. According to this mapping, the pixel values of the affected pixels are set, effective to perform the image editing operation.
-
7.发明授权公开(公告)号：US10165259B2
公开(公告)日：2018-12-25
申请号：US15433731
申请日：2017-02-15
IPC分类号： G06K9/00 , H04N13/282 , H04N13/02 , G06T7/70 , G06T7/00 , G06K9/62 , G06T7/194 , H04N13/00 , H04N13/161 , H04N13/275
摘要： Embodiments are directed towards providing a target view, from a target viewpoint, of a 3D object. A source image, from a source viewpoint and including a common portion of the object, is encoded in 2D data. An intermediate image that includes an intermediate view of the object is generated based on the data. The intermediate view is from the target viewpoint and includes the common portion of the object and a disoccluded portion of the object not visible in the source image. The intermediate image includes a common region and a disoccluded region corresponding to the disoccluded portion of the object. The disoccluded region is updated to include a visual representation of a prediction of the disoccluded portion of the object. The prediction is based on a trained image completion model. The target view is based on the common region and the updated disoccluded region of the intermediate image.
-
公开(公告)号：US10096125B1
公开(公告)日：2018-10-09
申请号：US15481564
申请日：2017-04-07
发明人： Jimei Yang , Yu-Wei Chao , Scott Cohen , Brian Price
摘要： 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：US20180232887A1
公开(公告)日：2018-08-16
申请号：US15950087
申请日：2018-04-10
发明人： Zhe Lin , Yibing Song , Xin Lu , Xiaohui Shen , Jimei Yang
CPC分类号： G06T7/13 , G06K9/00369 , G06K9/38 , G06K9/4628 , G06K9/66 , G06N3/0454 , G06N3/08 , G06N7/005 , G06T7/11 , G06T7/12 , G06T2207/20076 , G06T2207/20081
摘要： 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：US20190114748A1
公开(公告)日：2019-04-18
申请号：US15785359
申请日：2017-10-16
发明人： Zhe Lin , Xin Lu , Xiaohui Shen , Jimei Yang , Jiahui Yu
摘要： Digital image completion using deep learning is described. Initially, a digital image having at least one hole is received. This holey digital image is provided as input to an image completer formed with a framework that combines generative and discriminative neural networks based on learning architecture of the generative adversarial networks. From the holey digital image, the generative neural network generates a filled digital image having hole-filling content in place of holes. The discriminative neural networks detect whether the filled digital image and the hole-filling digital content correspond to or include computer-generated content or are photo-realistic. The generating and detecting are iteratively continued until the discriminative neural networks fail to detect computer-generated content for the filled digital image and hole-filling content or until detection surpasses a threshold difficulty. Responsive to this, the image completer outputs the filled digital image with hole-filling content in place of the holey digital image's holes.
-
-
-
-
-
-
-
-
-
搜索结果
19 条记录 (耗时 0.025 秒)
