专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明授权

US09870638B2 Appearance transfer techniques 有权
公开(公告)号：US09870638B2
公开(公告)日：2018-01-16
申请号：US15052552
申请日：2016-02-24
申请人： Ondrej Jamri{hacek over (s)}ka , Jakub Fiser , Paul J. Asente , Jingwan Lu , Elya Shechtman , Daniel Sýkora
发明人： Ondrej Jamri{hacek over (s)}ka , Jakub Fiser , Paul J. Asente , Jingwan Lu , Elya Shechtman , Daniel Sýkora
IPC分类号： G06T11/60 , G06T11/00 , G06T13/80 , G06T5/50 , G06K9/46 , G06K9/62 , G06K9/00 , G06K9/68 , H04N19/39 , H04N19/27 , H04N19/53 , G06T13/60 , G06T15/04
CPC分类号： G06T13/80 , G06T11/001 , G06T11/60 , G06T13/60 , G06T15/04 , G06T2210/24
摘要： Appearance transfer techniques are described in the following. In one example, a search and vote process is configured to select patches from the image exemplar and then search for a location in the target image that is a best fit for the patches. As part of this selection, a patch usage counter may also be employed in an example to ensure that selection of each of the patches from the image exemplar does not vary by more than one, one to another. In another example, transfer of an appearance of a boundary and interiors regions from the image exemplar to a target image is preserved.

22. 发明授权

US09852523B2 Appearance transfer techniques maintaining temporal coherence 有权
公开(公告)号：US09852523B2
公开(公告)日：2017-12-26
申请号：US15052710
申请日：2016-02-24
申请人： Ondrej Jamri{hacek over (s)}ka , Jakub Fiser , Paul J. Asente , Jingwan Lu , Elya Shechtman , Daniel Sýkora
发明人： Ondrej Jamri{hacek over (s)}ka , Jakub Fiser , Paul J. Asente , Jingwan Lu , Elya Shechtman , Daniel Sýkora
IPC分类号： G06T11/00 , G06T11/60 , G06T13/80 , H04N19/51 , H04N19/53 , H04N19/56 , H04N19/57
CPC分类号： G06T11/001 , G06T11/60 , G06T13/80 , G06T2210/24 , G06T2210/44
摘要： Appearance transfer techniques are described in the following that maintain temporal coherence between frames. In one example, a previous frame of a target video is warped that occurs in the sequence of the target video before a particular frame being synthesized. Color of the particular frame is transferred from an appearance of a corresponding frame of a video exemplar. In a further example, emitter portions are identified and addressed to preserve temporal coherence. This is performed to reduce an influence of the emitter portion of the target region in the selection of patches.

23. 发明授权

US08619098B2 Methods and apparatuses for generating co-salient thumbnails for digital images 有权
标题翻译：用于产生数字图像的共显着缩略图的方法和装置
公开(公告)号：US08619098B2
公开(公告)日：2013-12-31
申请号：US12868519
申请日：2010-08-25
申请人： Elya Shechtman , Daniel R. Goldman , David E. Jacobs
发明人： Elya Shechtman , Daniel R. Goldman , David E. Jacobs
IPC分类号： G09G5/02 , G09G5/14
CPC分类号： G09G5/14 , G06K9/6202 , G06K2009/6213 , G06T3/0012 , G06T11/60 , G06T2210/22 , G09G2320/0626 , G09G2320/0686 , G09G2320/08 , G09G2320/10 , G09G2340/12 , H04N1/3875
摘要： Methods and apparatus for generating context-sensitive, co-salient thumbnails are described. Co-salient thumbnails may effectively convey more useful information than conventional thumbnails while using the same or similar display space. As such, co-salient thumbnails may make it easier for a user to locate a particular image in a large collection of similar images. In some embodiments, for each of a plurality of patches in a first image, an illustrative method may identify a corresponding similar patch in a second image based on one or more similarity measures. The method may then determine a distance from each of the plurality of patches to its corresponding similar patch and select a crop in the first image relative to the second image based on the determined distance. Optionally, the method may repeat these operations in the opposite direction to select a crop in the second image relative to the first image.
摘要翻译：描述了用于生成上下文相关的，共显着的缩略图的方法和装置。在使用相同或相似的显示空间时，共显着的缩略图可以有效地传达比传统缩略图更有用的信息。因此，共显着的缩略图可以使得用户更容易在大量相似图像的大集合中定位特定图像。在一些实施例中，对于第一图像中的多个贴片中的每一个，说明性方法可以基于一个或多个相似性度量识别第二图像中的对应的相似贴片。该方法然后可以确定从多个补丁中的每一个到其对应的相似补丁的距离，并且基于所确定的距离来选择相对于第二图像的第一图像中的裁剪。可选地，该方法可以沿相反方向重复这些操作，以相对于第一图像选择第二图像中的裁剪。

24. 发明申请

US20130129213A1 Non-Rigid Dense Correspondence 有权
标题翻译：非刚性密集函数
公开(公告)号：US20130129213A1
公开(公告)日：2013-05-23
申请号：US13223202
申请日：2011-08-31
申请人： Elya Shechtman , Daniel Robert Goldman , Yoav HaCohen , Daniel Lischinski
发明人： Elya Shechtman , Daniel Robert Goldman , Yoav HaCohen , Daniel Lischinski
IPC分类号： G06K9/00
CPC分类号： G06T7/0028 , G06T7/33 , G06T2207/10024
摘要： Non-rigid dense correspondence (NRDC) for image enhancement may be performed. In one embodiment, a correspondence may be computed for each one of a plurality of regions of a source image to one of a plurality of regions of a reference image. Computing the correspondences may include searching within a search range for each of a plurality of image characteristics. One or more of the correspondences may be aggregated into matched regions. A global color transform and/or deblurring may be applied to the source image. In one embodiment, the global color transform and/or deblurring may be based on the matched regions. At least one of the search ranges may optionally be adjusted. In some embodiments, computing, aggregating, applying and/or deblurring, and adjusting may be iteratively performed.
摘要翻译：可以执行用于图像增强的非刚性密集对应（NRDC）。在一个实施例中，可以将源图像的多个区域中的每一个的对应关系计算为参考图像的多个区域之一。计算对应可以包括在搜索范围内搜索多个图像特征中的每一个。一个或多个通信可以被聚合成匹配的区域。全局颜色变换和/或去模糊可以应用于源图像。在一个实施例中，全局颜色变换和/或去模糊可以基于匹配区域。可以可选地调整至少一个搜索范围。在一些实施例中，可以迭代地执行计算，聚合，应用和/或去模糊和调整。

25. 发明申请

US20130121409A1 Methods and Apparatus for Face Fitting and Editing Applications 有权
标题翻译：面配和编辑应用的方法与装置
公开(公告)号：US20130121409A1
公开(公告)日：2013-05-16
申请号：US13408873
申请日：2012-02-29
申请人： Lubomir D. Bourdev , Elya Shechtman , Jue Wang , Fei Yang
发明人： Lubomir D. Bourdev , Elya Shechtman , Jue Wang , Fei Yang
IPC分类号： H04N7/26 , G06K9/00
CPC分类号： G06K9/00 , G06K9/00208 , G06K9/00288 , G06K9/00302 , G06K9/4671 , G06K9/6228 , G06T9/001
摘要： Various embodiments of methods and apparatus for face fitting are disclosed. In one embodiment, sets of two-dimensional local feature points on a face in each image of a set of images are identified. The set of images includes a sequence of frames a video stream. A three-dimensional face model for the face in the each image is generated as a combination of a set of predefined three-dimensional face models. In some embodiments, the generating includes reducing an error between a projection of vertices of the set of predefined three-dimensional face models and the two-dimensional local feature points of the each image, and constraining facial expression of the three-dimensional face model to change smoothly from image to image in the sequence of video frames.
摘要翻译：公开了用于面部装配的方法和装置的各种实施例。在一个实施例中，识别一组图像的每个图像中的脸上的二维局部特征点的集合。该组图像包括视频流的帧序列。作为一组预定义的三维面部模型的组合，生成每个图像中的面部的三维面部模型。在一些实施例中，生成包括减少预定义的三维面部模型的集合的顶点的投影与每个图像的二维局部特征点之间的误差，并且将三维面部模型的面部表情约束到在视频帧序列中，从图像平滑地改变成图像。

26. 发明申请

US20170243376A1 Appearance Transfer Techniques Maintaining Temporal Coherence 有权
公开(公告)号：US20170243376A1
公开(公告)日：2017-08-24
申请号：US15052710
申请日：2016-02-24
申请人： Ondrej Jamriska , Jakub Fiser , Paul J. Asente , Jingwan Lu , Elya Shechtman , Daniel Sýkora
发明人： Ondrej Jamriska , Jakub Fiser , Paul J. Asente , Jingwan Lu , Elya Shechtman , Daniel Sýkora
IPC分类号： G06T11/00 , G06T13/80 , G06T11/60
CPC分类号： G06T11/001 , G06T11/60 , G06T13/80 , G06T2210/24 , G06T2210/44
摘要： Appearance transfer techniques are described in the following that maintain temporal coherence between frames. In one example, a previous frame of a target video is warped that occurs in the sequence of the target video before a particular frame being synthesized. Color of the particular frame is transferred from an appearance of a corresponding frame of a video exemplar. In a further example, emitter portions are identified and addressed to preserve temporal coherence. This is performed to reduce an influence of the emitter portion of the target region in the selection of patches.

27. 发明授权

US09014470B2 Non-rigid dense correspondence 有权
标题翻译：非刚性密集通信
公开(公告)号：US09014470B2
公开(公告)日：2015-04-21
申请号：US13223202
申请日：2011-08-31
申请人： Elya Shechtman , Daniel Robert Goldman , Yoav HaCohen , Daniel Lischinski
发明人： Elya Shechtman , Daniel Robert Goldman , Yoav HaCohen , Daniel Lischinski
IPC分类号： G06K9/00 , G06T7/00
CPC分类号： G06T7/0028 , G06T7/33 , G06T2207/10024
摘要： Non-rigid dense correspondence (NRDC) for image enhancement may be performed. In one embodiment, a correspondence may be computed for each one of a plurality of regions of a source image to one of a plurality of regions of a reference image. Computing the correspondences may include searching within a search range for each of a plurality of image characteristics. One or more of the correspondences may be aggregated into matched regions. A global color transform and/or deblurring may be applied to the source image. In one embodiment, the global color transform and/or deblurring may be based on the matched regions. At least one of the search ranges may optionally be adjusted. In some embodiments, computing, aggregating, applying and/or deblurring, and adjusting may be iteratively performed.
摘要翻译：可以执行用于图像增强的非刚性密集对应（NRDC）。在一个实施例中，可以将源图像的多个区域中的每一个的对应关系计算为参考图像的多个区域之一。计算对应可以包括在搜索范围内搜索多个图像特征中的每一个。一个或多个通信可以被聚合成匹配的区域。全局颜色变换和/或去模糊可以应用于源图像。在一个实施例中，全局颜色变换和/或去模糊可以基于匹配区域。可以可选地调整至少一个搜索范围。在一些实施例中，可以迭代地执行计算，聚合，应用和/或去模糊和调整。

28. 发明授权

US08599219B2 Methods and apparatuses for generating thumbnail summaries for image collections 有权
标题翻译：用于生成图像集合缩略图摘要的方法和设备
公开(公告)号：US08599219B2
公开(公告)日：2013-12-03
申请号：US12868540
申请日：2010-08-25
申请人： Elya Shechtman , Daniel R. Goldman , David E. Jacobs
发明人： Elya Shechtman , Daniel R. Goldman , David E. Jacobs
IPC分类号： G09G5/02 , G06T3/40 , G06T11/00 , G06T15/50
CPC分类号： G06T3/4038 , G06F17/30274 , G06T3/0012 , G06T11/00 , G06T15/503
摘要： Methods and apparatuses for generating thumbnail summaries for image collections are described. Thumbnails summaries may be representative of the image collection while being disjoint from each other. In some embodiments, a method may sample crops from some or all images in an image collection. From these candidate crops, the method may select representative but disjoint crops. In some embodiments, a desired representativeness and/or disjointedness of the candidate crops may be defined by a user. The method may then generate and/or select thumbnail summaries for the collection of images based at least in part on the selected candidate crops.
摘要翻译：描述用于生成用于图像集合的缩略图摘要的方法和装置。缩略图摘要可能代表图像收集，而彼此不相交。在一些实施例中，方法可以从图像集合中的一些或所有图像中采集作物。从这些候选作物中，该方法可以选择代表性但不相交的作物。在一些实施例中，候选作物的期望代表性和/或不相容性可由用户定义。该方法然后可以至少部分地基于所选择的候选作物来生成和/或选择用于收集图像的缩略图摘要。

29. 发明授权

US08457442B1 Methods and apparatus for facial feature replacement 有权
标题翻译：面部特征置换的方法和装置
公开(公告)号：US08457442B1
公开(公告)日：2013-06-04
申请号：US12955071
申请日：2010-11-29
申请人： Jue Wang , Elya Shechtman , Lubomir D. Bourdev , Fei Yang
发明人： Jue Wang , Elya Shechtman , Lubomir D. Bourdev , Fei Yang
IPC分类号： G06K9/36
CPC分类号： G06K9/00 , G06T11/00 , G06T19/00 , G06T2210/44
摘要： A set of feature points for defining features of a face is detected in a target image and a reference image. The target image is warped to accommodate a selected feature from the reference image using the set of feature points and a set of three-dimensional models. The reference image is warped to a pose of the target image using the set of feature points and the set of three-dimensional models. The selected feature is copied from the reference image to the target image.
摘要翻译：在目标图像和参考图像中检测用于定义面部特征的一组特征点。使用一组特征点和一组三维模型，目标图像被扭曲以适应来自参考图像的所选特征。使用特征点集合和三维模型集合将参考图像扭曲成目标图像的姿态。所选功能从参考图像复制到目标图像。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式