专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 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。

2. 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。

3. 发明申请

US20130163874A1 Determining Correspondence Between Image Regions 有权
标题翻译：确定图像区域之间的对应关系
公开(公告)号：US20130163874A1
公开(公告)日：2013-06-27
申请号：US12857294
申请日：2010-08-16
申请人： Elya Shechtman , Dan Goldman , Connelly Barnes , Adam Finkelstein
发明人： Elya Shechtman , Dan Goldman , Connelly Barnes , Adam Finkelstein
IPC分类号： G06K9/46
CPC分类号： G06T7/0081 , G06K9/6211 , G06K2009/6213 , G06T7/337
摘要： Determining correspondence between image regions can include: selecting first and second regions of visual content including pixels in a computer system, the first region comprising a first patch to be mapped to the second region; selecting at least two heuristics for use in mapping the first patch to the second region, the heuristics selected from the group consisting of: (i) nearby-pixel mapping evaluation; (ii) random-perturbation mapping evaluation; (iii) evaluation of multiple mapping candidates identified in an iterative search process; and (iv) enrichment to increase a collection of mapping candidates; and identifying, using the selected heuristics, at least one patch in the second region for the first patch.
摘要翻译：确定图像区域之间的对应关系可以包括：选择包括计算机系统中的像素的视觉内容的第一和第二区域，第一区域包括要映射到第二区域的第一贴片; 选择至少两个启发式用于将第一贴片映射到第二区域，所述启发式选择自：（i）附近像素映射评估; （ii）随机扰动映射评估; （iii）评估在迭代搜索过程中识别的多个映射候选; （iv）丰富地图候选人; 以及使用所选择的启发式方法来识别所述第二区域中的至少一个贴片用于所述第一贴片。

4. 发明申请

US20130129141A1 Methods and Apparatus for Facial Feature Replacement 有权
标题翻译：面部特征替代方法和装置
公开(公告)号：US20130129141A1
公开(公告)日：2013-05-23
申请号：US12954487
申请日：2010-11-24
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： G06K9/00
CPC分类号： G06K9/00 , G06T11/00 , G06T19/00 , G06T2210/44
摘要： Three dimensional models corresponding to a target image and a reference image are selected based on a set of feature points defining facial features in the target image and the reference image. The set of feature points defining the facial features in the target image and the reference image are associated with corresponding 3-dimensional models. A 3D motion flow between the 3-dimensional models is computed. The 3D motion flow is projected onto a 2D image plane to create a 2D optical field flow. The target image and the reference image are warped using the 2D optical field flow. A selected feature from the reference image is copied to the target image.
摘要翻译：基于定义目标图像和参考图像中的面部特征的一组特征点来选择与目标图像和参考图像相对应的三维模型。定义目标图像和参考图像中的面部特征的特征点集合与相应的三维模型相关联。计算3维模型之间的3D运动流。将3D运动流投影到2D图像平面上以产生2D光场流。使用2D光场流使目标图像和参考图像翘曲。来自参考图像的所选特征被复制到目标图像。

5. 发明授权

US08407575B1 Video content summary 有权
标题翻译：视频内容摘要
公开(公告)号：US08407575B1
公开(公告)日：2013-03-26
申请号：US12315038
申请日：2008-11-26
申请人： Dan Goldman , Connelly Barnes , Elya Shechtman
发明人： Dan Goldman , Connelly Barnes , Elya Shechtman
IPC分类号： G06F17/00
CPC分类号： G06F17/30843
摘要： Among other disclosed subject matter, a computer program product is tangibly embodied in a tangible program carrier and includes instructions that when executed by a processor perform a method. The method includes obtaining a plurality of layouts generated from video content, each of the layouts comprising a visual summary of the video content at a respective zoom level, each visual summary including a plurality of frames selected from the video content and blended into the corresponding layout without borders between the frames. The method includes creating an animation between the plurality of layouts so that a user can zoom continuously between the zoom levels to view the visual summaries of the video content.
摘要翻译：在其他公开的主题中，计算机程序产品有形地体现在有形程序载体中，并且包括当由处理器执行时执行方法的指令。该方法包括获得从视频内容生成的多个布局，每个布局包括各自缩放级别的视频内容的视觉概要，每个视觉摘要包括从视频内容中选择的多个帧并且混合到相应的布局没有框架之间的边框。该方法包括在多个布局之间创建动画，使得用户可以在缩放级别之间连续缩放以查看视频内容的视觉摘要。

6. 发明申请

US20130051685A1 PATCH-BASED SYNTHESIS TECHNIQUES 有权
标题翻译：基于PATCH的合成技术
公开(公告)号：US20130051685A1
公开(公告)日：2013-02-28
申请号：US13565552
申请日：2012-08-02
申请人： Elya Shechtman , Daniel R. Goldman , Aliakbar Darabi
发明人： Elya Shechtman , Daniel R. Goldman , Aliakbar Darabi
IPC分类号： G06K9/68
CPC分类号： G06K9/4652 , G06K9/00 , G06K9/6202 , G06K9/68 , G06T11/60
摘要： Methods, apparatus, and computer-readable storage media for patch-based image synthesis. A patch matching technique provides an extended patch search space that encompasses geometric and photometric transformations, as well as gradient domain features. The geometric transformations may include translation, rotation, reflection, scale, and non-uniform scale. The photometric transformations may include gain and bias. Patch-based image synthesis techniques may leverage the extended patch search space in various image synthesis applications. The patch-based image synthesis techniques may also integrate image gradients into the patch representation and replace conventional color averaging with a technique that performs voting for colors and gradients and then solves a screened Poisson equation based on values for colors and gradients when blending patch(es) with a target image.
摘要翻译：用于基于贴片的图像合成的方法，装置和计算机可读存储介质。补丁匹配技术提供了包含几何和光度变换以及梯度域特征的扩展补丁搜索空间。几何变换可以包括平移，旋转，反射，缩放和非均匀尺度。光度变换可以包括增益和偏置。基于补丁的图像合成技术可以利用各种图像合成应用中的扩展补丁搜索空间。基于贴片的图像合成技术还可以将图像渐变集成到贴片表示中并且用对颜色和渐变进行投票的技术来代替常规颜色平均化，然后基于色彩和梯度的值来解决屏幕Poisson方程）与目标图像。

7. 发明授权

US08285055B1 Determining correspondence between image regions 有权
标题翻译：确定图像区域之间的对应关系
公开(公告)号：US08285055B1
公开(公告)日：2012-10-09
申请号：US12394280
申请日：2009-02-27
申请人： Connelly Barnes , Dan Goldman , Elya Shechtman
发明人： Connelly Barnes , Dan Goldman , Elya Shechtman
IPC分类号： G06K9/46
CPC分类号： G06T7/337
摘要： Determining correspondence between image regions includes identifying first and second regions of visual content including pixels in a computer system. The first region includes a first patch of pixels having a first mapping to a second patch of pixels in the second region. Iterative evaluations of the first and second regions are performed, each including at least (i) a first evaluation phase selecting a best mapping for the first patch, according to a distance metric, the best mapping selected from among the first mapping and a second mapping obtained from mappings of nearby pixels, and (ii) a second evaluation phase selecting one of the best mapping and a third mapping obtained by perturbing the second mapping. A result of the iterative evaluations is recorded in the computer system that indicates a third patch of pixels in the second region identified in the iterative evaluations.
摘要翻译：确定图像区域之间的对应关系包括识别包括计算机系统中的像素的视觉内容的第一和第二区域。第一区域包括第一贴片像素，其具有与第二区域中的第二像素块的第一映射。执行第一和第二区域的迭代评估，每个包括至少（i）第一评估阶段，根据距离度量选择第一贴片的最佳映射，从第一映射和第二映射中选择的最佳映射从邻近像素的映射获得，以及（ii）选择最佳映射之一的第二评估阶段和通过扰乱第二映射而获得的第三映射。迭代评估的结果被记录在计算机系统中，其指示在迭代评估中识别的第二区域中的第三个像素块。

8. 发明申请

US20170358128A1 Illumination-Guided Example-Based Stylization of 3D Renderings 有权
公开(公告)号：US20170358128A1
公开(公告)日：2017-12-14
申请号：US15178072
申请日：2016-06-09
申请人： Jakub Fiser , Ondrej Jamriska , Michal Lukác , Elya Shechtman , Paul J. Asente , Jingwan Lu , Daniel Sýkora
发明人： Jakub Fiser , Ondrej Jamriska , Michal Lukác , Elya Shechtman , Paul J. Asente , Jingwan Lu , Daniel Sýkora
IPC分类号： G06T15/50 , G06T15/02 , G06T15/60 , G06T15/80
CPC分类号： G06T15/503 , G06T11/60 , G06T15/02 , G06T15/60 , G06T15/80 , G06T19/20 , G06T2219/2024
摘要： Techniques for illumination-guided example-based stylization of 3D renderings are described. In implementations, a source image and a target image are obtained, where each image includes a multi-channel image having at least a style channel and multiple light path expression (LPE) channels having light propagation information. Then, the style channel of the target image is synthesized to mimic a stylization of individual illumination effects from the style channel of the source image. As part of the synthesizing, the light propagation information is applied as guidance for synthesis of the style channel of the target image. Based on the guidance, the stylization of individual illumination effects from the style channel of the source image is transferred to the style channel of the target image. Based on the transfer, the style channel of the target image is then generated for display of the target image via a display device.

9. 发明授权

US08861868B2 Patch-based synthesis techniques 有权
标题翻译：基于贴片的综合技术
公开(公告)号：US08861868B2
公开(公告)日：2014-10-14
申请号：US13565552
申请日：2012-08-02
申请人： Elya Shechtman , Daniel R. Goldman , Aliakbar Darabi
发明人： Elya Shechtman , Daniel R. Goldman , Aliakbar Darabi
IPC分类号： G06K9/68 , G06T11/60
CPC分类号： G06K9/4652 , G06K9/00 , G06K9/6202 , G06K9/68 , G06T11/60
摘要： Methods, apparatus, and computer-readable storage media for patch-based image synthesis. A patch matching technique provides an extended patch search space that encompasses geometric and photometric transformations, as well as gradient domain features. The geometric transformations may include translation, rotation, reflection, scale, and non-uniform scale. The photometric transformations may include gain and bias. Patch-based image synthesis techniques may leverage the extended patch search space in various image synthesis applications. The patch-based image synthesis techniques may also integrate image gradients into the patch representation and replace conventional color averaging with a technique that performs voting for colors and gradients and then solves a screened Poisson equation based on values for colors and gradients when blending patch(es) with a target image.
摘要翻译：用于基于贴片的图像合成的方法，装置和计算机可读存储介质。补丁匹配技术提供了包含几何和光度变换以及梯度域特征的扩展补丁搜索空间。几何变换可以包括平移，旋转，反射，缩放和非均匀尺度。光度变换可以包括增益和偏置。基于补丁的图像合成技术可以利用各种图像合成应用中的扩展补丁搜索空间。基于贴片的图像合成技术还可以将图像渐变集成到贴片表示中并且用对颜色和渐变进行投票的技术来代替常规颜色平均化，然后基于色彩和梯度的值来解决屏幕Poisson方程）与目标图像。

10. 发明授权

US08818135B1 Low memory content aware fill 有权
标题翻译：低内存含量意识填充
公开(公告)号：US08818135B1
公开(公告)日：2014-08-26
申请号：US13652548
申请日：2012-10-16
申请人： Dan Goldman , Elya Shechtman
发明人： Dan Goldman , Elya Shechtman
IPC分类号： G06K9/32
CPC分类号： G06T1/60 , G06T5/005 , G06T2207/20021 , G06T2207/20172
摘要： A first image at a first resolution is received, the first image having a first hole therein. Based on the first image, a second image is generated at a second resolution lower than the first resolution, the second image having a second hole therein corresponding to the first hole. In the second image, one or more second-image source patches for the second hole are identified. At least one first-image source patch in the first image is identified based on a location of the identified second-image source patch. The identified at least one first-image source patch are stored in memory. Fill content are identified in the at least one first-image source patch stored in the memory. The identified fill content are placed in the first hole.
摘要翻译：接收第一分辨率的第一图像，第一图像在其中具有第一孔。基于第一图像，以比第一分辨率低的第二分辨率产生第二图像，第二图像在其中具有与第一孔相对应的第二孔。在第二图像中，识别用于第二孔的一个或多个第二图像源补丁。基于所识别的第二图像源补丁的位置来识别第一图像中的至少一个第一图像源补丁。所识别的至少一个第一图像源补丁存储在存储器中。填充内容在存储在存储器中的至少一个第一图像源补丁中被识别。所识别的填充内容被放置在第一个孔中。

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