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. 发明授权

US08780135B2 System and method for reducing the appearance of residuals in gradient-based image compositing 有权
标题翻译：用于减少基于梯度的图像合成中残差出现的系统和方法
公开(公告)号：US08780135B2
公开(公告)日：2014-07-15
申请号：US12393881
申请日：2009-02-26
申请人： Sylvain Paris
发明人： Sylvain Paris
IPC分类号： G06T11/60
CPC分类号： G06T11/60 , G09G2320/0266 , G09G2340/12
摘要： A system and method are proposed for performing gradient-based compositing in a manner that reduces the appearance of residual errors as compared to traditional techniques. In embodiments, a target gradient field may be determined for a composite image and a solution composite image may be sought which minimizes a weighted aggregate error between the gradient field of the composite image and the target gradient field. The weighted aggregate error may be calculated such that a greater weight is placed on residuals occurring in smooth regions than on those occurring in textured regions, since residuals in textured regions may be less noticeable. In some embodiments, a weighted aggregate error may be defined as a weighted least-squares sum and/or minimized by solving a weighted Poisson equation. The computational cost of solving the weighted Poisson equation may be mitigated by ensuring that the equation is linear.
摘要翻译：提出了一种系统和方法，用于以与传统技术相比减少残余误差的出现的方式执行基于梯度的合成。在实施例中，可以针对合成图像确定目标梯度场，并且可以搜索解最小化合成图像的梯度场与目标梯度场之间的加权聚集误差的解决方案合成图像。可以计算加权聚集误差，使得在平滑区域中发生的残余物上比在纹理区域中发生的残余物更大的权重，因为纹理区域中的残差可能不那么显着。在一些实施例中，加权聚合误差可以通过求解加权泊松方程来定义为加权最小二乘和和/或最小化。通过确定方程是线性的，可以减轻求解加权泊松方程的计算成本。

2. 发明授权

US08699858B2 Combined visual and auditory processing 有权
标题翻译：组合视觉和听觉处理
公开(公告)号：US08699858B2
公开(公告)日：2014-04-15
申请号：US12323738
申请日：2008-11-26
申请人： Ce Liu , Sylvain Paris , Paris Smaragdis , Wojciech Matusik
发明人： Ce Liu , Sylvain Paris , Paris Smaragdis , Wojciech Matusik
IPC分类号： H04N5/93 , G11B27/00 , G11B27/031 , G06T7/00 , H04N5/222
CPC分类号： G11B27/031 , G06T7/11 , G06T7/136 , G06T2207/10024 , G11B27/00 , G11B27/034 , G11B27/28 , H04N5/2226
摘要： A computer-implemented method includes segmenting a plurality of video frames of a sequence of video frames into a first portion that includes a selected visual object represented in the video frame and a second portion that includes a background represented in the video frame. The selected visual object is selected by using a selection envelope.
摘要翻译：计算机实现的方法包括将视频帧序列的多个视频帧分割成包括在视频帧中表示的所选视觉对象的第一部分和包括在视频帧中表示的背景的第二部分。通过使用选择信封来选择所选择的视觉对象。

3. 发明申请

US20130121572A1 Methods and Apparatus for Tone Mapping High Dynamic Range Images 有权
标题翻译：用于色调映射高动态范围图像的方法和装置
公开(公告)号：US20130121572A1
公开(公告)日：2013-05-16
申请号：US12695100
申请日：2010-01-27
申请人： Sylvain Paris , Jen-Chan Chien , Eric Chan
发明人： Sylvain Paris , Jen-Chan Chien , Eric Chan
IPC分类号： G06K9/36
CPC分类号： G06T5/008 , G06F3/04845 , G06T5/007 , G06T5/40 , G06T5/50 , G06T11/001 , G06T2207/10024 , G06T2207/20092 , G06T2207/20192 , G06T2207/20208 , G06T2207/20221 , H04N1/6027 , H04N19/30
摘要： Methods, apparatus, and computer-readable storage media for tone mapping High Dynamic Range (HDR) images. An input HDR image is separated into luminance and color. Luminance is processed to obtain a base layer and a detail layer. The base layer is compressed according to a non-linear remapping function to reduce the dynamic range, and the detail layer is adjusted. The layers are combined to generate output luminance, and the output luminance and color are combined to generate an output image. A base layer compression technique may be used that analyzes the details and compresses the base layer accordingly to provide space at the top of the intensity scale where the details are displayed to thus generate output images that are visually better than images generated using conventional techniques. User interface elements may be provided via which a user may control one or more parameters of the tone mapping method.
摘要翻译：用于色调映射高动态范围（HDR）图像的方法，装置和计算机可读存储介质。输入HDR图像被分成亮度和颜色。处理亮度以获得基层和细节层。根据非线性重映射功能对基本层进行压缩以减小动态范围，调整细节层。这些层被组合以产生输出亮度，并且输出亮度和颜色被组合以产生输出图像。可以使用基层压缩技术，其分析细节并相应地压缩基层，以在显示细节的强度标度的顶部提供空间，从而生成视觉上优于使用常规技术产生的图像的输出图像。可以提供用户界面元素，用户可以经由该用户界面元素来控制色调映射方法的一个或多个参数。

4. 发明申请

US20130121566A1 Automatic Image Adjustment Parameter Correction 有权
公开(公告)号：US20130121566A1
公开(公告)日：2013-05-16
申请号：US13430459
申请日：2012-03-26
申请人： Sylvain Paris , Jen-Chan Chien , Vladimir Leonid Bychkovsky
发明人： Sylvain Paris , Jen-Chan Chien , Vladimir Leonid Bychkovsky
IPC分类号： G06K9/62
CPC分类号： G06T5/009 , G06K9/00275 , G06K9/00684 , G06T11/001 , G06T2207/20081 , G06T2207/20092 , H04N1/32251
摘要： Techniques are disclosed relating to modifying an automatically predicted adjustment. In one embodiment, the automatically predicted adjustment may be adjusted, for example, based on a rule. The automatically predicted adjustment may be based on a machine learning prediction. A new image may be globally adjusted based on the modified automatically predicted adjustment.

5. 发明授权

US07945107B2 System and method for providing gradient preservation for image processing 有权
标题翻译：提供图像处理梯度保存的系统和方法
公开(公告)号：US07945107B2
公开(公告)日：2011-05-17
申请号：US11725096
申请日：2007-03-16
申请人： Soonmin Bae , Fréderic Durand , Sylvain Paris
发明人： Soonmin Bae , Fréderic Durand , Sylvain Paris
IPC分类号： G06K9/40
CPC分类号： G06T5/50 , G06T5/007 , G06T5/40 , G06T7/44 , G06T2207/20028 , G06T2207/20192 , G06T2207/20208
摘要： The present invention provides gradient preservation of an input image. A method of providing gradient preservation of an input image, comprises the steps of: computing gradient fields of the input image; computing gradient fields of a remapped image, wherein the remapped image is the input image remapped; comparing a gradient of the remapped image to a predefined range of acceptable values, wherein the acceptable values depend on the input gradient; changing values of the gradient of the remapped image if the values of the gradient of the remapped image are not within the predefined range of acceptable values depending on the input gradient, resulting in x and y components of a modified gradient; and reconstructing the input image using the x and y components of the modified gradient.
摘要翻译：本发明提供输入图像的梯度保存。提供输入图像的梯度保存的方法包括以下步骤：计算输入图像的梯度场; 计算重映射图像的梯度场，其中重新映射的图像是重新映射的输入图像; 将重映射图像的梯度与可接受值的预定范围进行比较，其中可接受值取决于输入梯度; 如果重映射图像的梯度的值不在取决于输入梯度的可接受值的预定范围内，则改变重映射图像的梯度的值，导致修改梯度的x和y分量; 并使用修改的梯度的x和y分量来重建输入图像。

6. 发明申请

US20080226168A1 System and method for providing two-scale tone management of an image 有权
标题翻译：提供图像两度色调管理的系统和方法
公开(公告)号：US20080226168A1
公开(公告)日：2008-09-18
申请号：US11725095
申请日：2007-03-16
申请人： Soonmin Bae , Frederic Durand , Sylvain Paris
发明人： Soonmin Bae , Frederic Durand , Sylvain Paris
IPC分类号： G06K9/34
CPC分类号： G06T5/007 , G06T5/40 , G06T2207/20028
摘要： The present invention provides two-scale tone management of an input image. A method of providing two-scale tone management contains the steps of: separating the input image into a base layer and a detail layer; separating a model image into a base layer and a detail layer; analyzing the input image globally for global contrast; analyzing the input image locally for local contrast; and performing detail preservation of the input image. A system contains a memory and a processor, where the processor is configured by the memory to perform the steps of: separating the input image into a base layer and a detail layer; separating a model image into a base layer and a detail layer; analyzing the input image globally for global contrast; analyzing the input image locally for local contrast; and performing detail preservation of the input image.
摘要翻译：本发明提供了输入图像的两尺度音调管理。提供两级音调管理的方法包括以下步骤：将输入图像分离成基本层和细节层; 将模型图像分离成基本层和细节层; 全局对比分析输入图像; 本地分析输入图像以进行局部对比度; 并执行输入图像的细节保存。系统包含存储器和处理器，其中处理器由存储器配置以执行以下步骤：将输入图像分离成基本层和细节层; 将模型图像分离成基本层和细节层; 全局对比分析输入图像; 本地分析输入图像以进行局部对比度; 并执行输入图像的细节保存。

7. 发明授权

US08903169B1 Automatic adaptation to image processing pipeline 有权
公开(公告)号：US08903169B1
公开(公告)日：2014-12-02
申请号：US13430488
申请日：2012-03-26
申请人： Sylvain Paris , Jen-Chan Chien , Vladimir Leonid Bychkovsky
发明人： Sylvain Paris , Jen-Chan Chien , Vladimir Leonid Bychkovsky
IPC分类号： G06K9/62
CPC分类号： G06K9/6256 , G06F17/30247 , G06K9/00624 , G06T1/20 , G06T5/00 , G06T2207/20081
摘要： Techniques are disclosed relating to generating generic labels, translating generic labels to image pipeline-specific labels, and automatically adjusting images. In one embodiment, generic labels may be generated. Generic algorithm parameters may be generated based on training a regression algorithm with the generic labels. The generic labels may be translated to pipeline-specific labels, which may be usable to automatically adjust an image.

8. 发明授权

US08666148B2 Image adjustment 有权
标题翻译：图像调整
公开(公告)号：US08666148B2
公开(公告)日：2014-03-04
申请号：US13036245
申请日：2011-02-28
申请人： Sylvain Paris , Frederic P. Durand , Vladimir Leonid Bychkovsky , Eric Chan
发明人： Sylvain Paris , Frederic P. Durand , Vladimir Leonid Bychkovsky , Eric Chan
IPC分类号： G06K9/62
CPC分类号： G06K9/6256 , G06K9/00 , G06K9/62 , G06T5/009 , G06T2207/10024 , G06T2207/20076 , G06T2207/20081
摘要： Techniques are disclosed relating to automatically adjusting images. In one embodiment, an image may be automatically adjusted based on a regression model trained with a database of raw and adjusted images. In one embodiment, an image may be automatically adjusted based on a model trained by both a database of raw and adjusted images and a small set of images adjusted by a different user. In one embodiment, an image may be automatically adjusted based on a model trained by a database of raw and adjusted images and predicted differences between a user's adjustment to a small set of images and a predicted adjustment based on the database of raw and adjusted images.
摘要翻译：公开了关于自动调整图像的技术。在一个实施例中，可以基于用原始和调整图像的数据库训练的回归模型来自动调整图像。在一个实施例中，可以基于由原始和调整图像的数据库和由不同用户调整的一组小图像训练的模型来自动调整图像。在一个实施例中，可以基于由原始和调整图像的数据库训练的模型以及用户对小图像集的调整之间的预测差异以及基于原始和调整图像的数据库的预测调整来自动调整图像。

9. 发明授权

US08520972B2 Image decomposition 有权
标题翻译：图像分解
公开(公告)号：US08520972B2
公开(公告)日：2013-08-27
申请号：US12323663
申请日：2008-11-26
申请人： Kalyan Sunkavalli , Sylvain Paris , Wojciech Matusik
发明人： Kalyan Sunkavalli , Sylvain Paris , Wojciech Matusik
IPC分类号： G06K9/40
CPC分类号： G06T7/162 , G06T7/11 , G06T2207/30196
摘要： A computer-implemented method includes segmenting an input image into a plurality of image cues, each image cue representing a unique set of pixels of the input image. For each image cue, the method includes determining a set of image components, wherein each image component is associated with at least one adjustable factor to represent at least one characteristic of the image cue.
摘要翻译：计算机实现的方法包括将输入图像分割成多个图像提示，每个图像提示表示输入图像的唯一的像素集合。对于每个图像提示，该方法包括确定一组图像分量，其中每个图像分量与至少一个可调节因子相关联以表示图像提示的至少一个特征。

10. 发明授权

US08447769B1 System and method for real-time image collection and sharing 有权
标题翻译：用于实时图像采集和共享的系统和方法
公开(公告)号：US08447769B1
公开(公告)日：2013-05-21
申请号：US12868490
申请日：2010-08-25
申请人： Sylvain Paris , Paul E. Green , Shmuel Avidan , William T. Freeman , Wojciech Matusik
发明人： Sylvain Paris , Paul E. Green , Shmuel Avidan , William T. Freeman , Wojciech Matusik
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/3028
摘要： Various embodiments of a system and methods for real-time image collection and sharing are described. A group of geographically co-located mobile device users may capture images on the mobile devices during a session. The devices may send the images, during the same session, to a database where the images may be stored as a real-time image collection. The image collection may be shared, during the same session, among the mobile device users. The users may receive notification of new images in the image collection based on user preferences. The users may request, from the image collection, images containing particular content by identifying the content on an image and sending a search request which includes the identified content. A computation server may maintain a data set which associates similar images in the image collection. The data set may be updated for each new image that is added to the image collection.
摘要翻译：描述了用于实时图像收集和共享的系统和方法的各种实施例。一组地理位置相同的移动设备用户可以在会话期间在移动设备上捕获图像。设备可以在同一会话期间将图像发送到图像可以被存储为实时图像集合的数据库。可以在同一会话期间在移动设备用户之间共享图像集合。用户可以基于用户偏好接收图像集合中的新图像的通知。用户可以通过识别图像上的内容并发送包括所识别的内容的搜索请求，从图像集合中请求包含特定内容的图像。计算服务器可以维护在图像集合中关联类似图像的数据集。可以为添加到图像集合的每个新图像更新数据集。

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