-
1.发明授权System and methods of compressed sensing as applied to computer graphics and computer imaging 有权压缩感知的系统和方法应用于计算机图形学和计算机成像公开(公告)号：US08666180B2
公开(公告)日：2014-03-04
申请号：US13512951
申请日：2010-12-03
申请人： Pradeep Sen , Aliakbar Darabi
发明人： Pradeep Sen , Aliakbar Darabi
摘要： Compressed sensing can be mapped to a more general set of problems in computer graphics and computer imaging. Representation of a rendered scene in the formulation y=A{circumflex over (x)} produces higher-quality rendering with less samples than previous approaches. A filter formulation Φ makes point samples compatible with wavelet and therefore allows reconstruction of 2-D images from a set of measured pixels (point samples).
摘要翻译： 压缩感测可以映射到计算机图形学和计算机成像中更一般的问题集。 在制定中，渲染场景的表示y = A {在（x）}中生成比以前的方法更少的样本的更高品质的渲染。 滤波器公式Phi使点样本与小波兼容，因此允许从一组测量像素（点样本）重建2-D图像。
-
2.发明申请SYSTEM AND METHODS OF COMPRESSED SENSING AS APPLIED TO COMPUTER GRAPHICS AND COMPUTER IMAGING 有权压缩感应系统和方法应用于计算机图形和计算机成像公开(公告)号：US20120294543A1
公开(公告)日：2012-11-22
申请号：US13512951
申请日：2010-12-03
申请人： Pradeep Sen , Aliakbar Darabi
发明人： Pradeep Sen , Aliakbar Darabi
IPC分类号： G06T1/00
摘要： Compressed sensing can be mapped to a more general set of problems in computer graphics and computer imaging. Representation of a rendered scene in the formulation y=Âx produces higher-quality rendering with less samples than previous approaches. A filter formulation Φ makes point samples compatible with wavelet and therefore allows reconstruction of 2-D images from a set of measured pixels (point samples).
摘要翻译： 压缩感测可以映射到计算机图形学和计算机成像中更一般的问题集。 在制定y = x中，渲染场景的表示会产生比以前的方法更少的样本的较高质量的渲染。 滤波器公式Φ使得点样本与小波兼容，因此允许从一组测量像素（点样本）重建二维图像。
-
公开(公告)号：US20140029849A1
公开(公告)日：2014-01-30
申请号：US13980230
申请日：2012-01-17
申请人： Pradeep Sen , Aliakbar Darabi
发明人： Pradeep Sen , Aliakbar Darabi
IPC分类号： G06T5/00
CPC分类号： G06T5/001 , G06T5/00 , G06T5/50 , G06T15/503 , G06T2200/12 , G06T2207/20221
摘要： The invention produces a higher quality image from a rendering system based on a relationship between the output of a rendering system and the parameters used to compute them. Specifically, noise is removed in rendering by estimating the functional dependency between sample features and the random inputs to the system. Mutual information is applied to a local neighborhood of samples in each part of the image. This dependency is then used to reduce the importance of certain scene features in a cross-bilateral filter, which preserves scene detail. The results produced by the invention are computed in a few minutes thereby making it reasonably robust for use in production environments.
摘要翻译： 本发明基于渲染系统的输出与用于计算它们的参数之间的关系从渲染系统产生更高质量的图像。 具体来说，通过估计样本特征与系统的随机输入之间的功能依赖性，在渲染中消除噪声。 相互信息被应用于图像的每个部分中的样本的局部邻域。 然后，这种依赖关系用于减少跨双边筛选器中某些场景特征的重要性，这保留了场景细节。 本发明产生的结果在几分钟内计算，从而使其在生产环境中的使用相当稳健。
-
公开(公告)号：US08712180B2
公开(公告)日：2014-04-29
申请号：US13980230
申请日：2012-01-17
申请人： Pradeep Sen , Aliakbar Darabi
发明人： Pradeep Sen , Aliakbar Darabi
CPC分类号： G06T5/001 , G06T5/00 , G06T5/50 , G06T15/503 , G06T2200/12 , G06T2207/20221
摘要： The invention produces a higher quality image from a rendering system based on a relationship between the output of a rendering system and the parameters used to compute them. Specifically, noise is removed in rendering by estimating the functional dependency between sample features and the random inputs to the system. Mutual information is applied to a local neighborhood of samples in each part of the image. This dependency is then used to reduce the importance of certain scene features in a cross-bilateral filter, which preserves scene detail. The results produced by the invention are computed in a few minutes thereby making it reasonably robust for use in production environments.
摘要翻译： 本发明基于渲染系统的输出与用于计算它们的参数之间的关系从渲染系统产生更高质量的图像。 具体来说，通过估计样本特征与系统的随机输入之间的功能依赖性，在渲染中消除噪声。 相互信息被应用于图像的每个部分中的样本的局部邻域。 然后，这种依赖关系用于减少跨双边筛选器中某些场景特征的重要性，这保留了场景细节。 本发明产生的结果在几分钟内计算，从而使其在生产环境中的使用相当稳健。
-
公开(公告)号：US08861868B2
公开(公告)日：2014-10-14
申请号：US13565552
申请日：2012-08-02
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。
-
公开(公告)号：US20130051685A1
公开(公告)日：2013-02-28
申请号：US13565552
申请日：2012-08-02
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。
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.017 秒)
