-
公开(公告)号：US08855411B2
公开(公告)日：2014-10-07
申请号：US13108945
申请日：2011-05-16
申请人： Kaiming He , Jian Sun , Carsten Curt Eckard Rother , Xiao-Ou Tang
发明人： Kaiming He , Jian Sun , Carsten Curt Eckard Rother , Xiao-Ou Tang
摘要： A computing device is described herein that is configured to select a pixel pair including a foreground pixel of an image and a background pixel of the image from a global set of pixels based at least on spatial distances from an unknown pixel and color distances from the unknown pixel. The computing device is further configured to determine an opacity measure for the unknown pixel based at least on the selected pixel pair.
摘要翻译： 本文描述了一种计算设备，其被配置为至少基于与未知像素的空间距离和来自未知像素的颜色距离从全局像素集合中选择包括图像的前景像素和图像的背景像素的像素对 像素。 计算设备还被配置为至少基于所选择的像素对来确定未知像素的不透明度测量。
-
公开(公告)号：US08605992B2
公开(公告)日：2013-12-10
申请号：US13083271
申请日：2011-04-08
CPC分类号： G06T5/005 , G06T2207/10004 , G06T2207/10024 , G06T2207/10028
摘要： Image completion using scene geometry is described, for example, to remove marks from digital photographs or complete regions which are blank due to editing. In an embodiment an image depicting, from a viewpoint, a scene of textured objects has regions to be completed. In an example, geometry of the scene is estimated from a depth map and the geometry used to warp the image so that at least some surfaces depicted in the image are fronto-parallel to the viewpoint. An image completion process is guided using distortion applied during the warping. For example, patches used to fill the regions are selected on the basis of distortion introduced by the warping. In examples where the scene comprises regions having only planar surfaces the warping process comprises rotating the image. Where the scene comprises non-planar surfaces, geodesic distances between image elements may be scaled to flatten the non-planar surfaces.
摘要翻译： 描述使用场景几何的图像完成，例如，从数字照片或由于编辑而为空的完整区域中移除标记。 在一个实施例中，从视点描绘纹理对象的场景的图像具有要完成的区域。 在一个示例中，从深度图和用于扭曲图像的几何估计场景的几何形状，使得图像中描绘的至少一些表面与视点平行。 使用在翘曲期间施加的变形来指导图像完成处理。 例如，基于由翘曲引入的失真来选择用于填充区域的补丁。 在场景包括仅具有平面表面的区域的示例中，翘曲过程包括旋转图像。 在场景包括非平面表面的情况下，图像元素之间的测地距离可以被缩放以平坦化非平面表面。
-
公开(公告)号：US20110216975A1
公开(公告)日：2011-09-08
申请号：US12718232
申请日：2010-03-05
摘要： A method of up-sampling binary images for segmentation is described. In an embodiment, digital images are down-sampled before segmentation. The resulting initial binary segmentation, which has a lower resolution than the original image, is then up-sampled and smoothed to generate an interim non-binary solution which has a higher resolution than the initial binary segmentation. The final binary segmentation for the image is then computed from the interim non-binary solution based on a threshold. This method does not use the original image data in inferring the final binary segmentation solution from the initial binary segmentation. In an embodiment, the method may be applied to all images and in another embodiment, the method may be used for images which comprise a large number of pixels in total or in single dimension and smaller images may not be down-sampled before segmentation.
摘要翻译： 描述了用于分割的二进制图像的上采样方法。 在一个实施例中，在分割之前对数字图像进行下采样。 然后，所得到的具有比原始图像更低分辨率的初始二进制分割被上采样和平滑以产生具有比初始二进制分割更高分辨率的临时非二进制解。 然后基于阈值从临时非二进制解决方案计算图像的最终二进制分割。 该方法不使用原始图像数据从最初的二进制分割推断最终的二进制分割解决方案。 在一个实施例中，该方法可以应用于所有图像，并且在另一个实施例中，该方法可以用于总共或单维度中包含大量像素的图像，并且在分割之前可能不会对较小的图像进行下采样。
-
公开(公告)号：US08411948B2
公开(公告)日：2013-04-02
申请号：US12718232
申请日：2010-03-05
摘要： A method of up-sampling binary images for segmentation is described. In an embodiment, digital images are down-sampled before segmentation. The resulting initial binary segmentation, which has a lower resolution than the original image, is then up-sampled and smoothed to generate an interim non-binary solution which has a higher resolution than the initial binary segmentation. The final binary segmentation for the image is then computed from the interim non-binary solution based on a threshold. This method does not use the original image data in inferring the final binary segmentation solution from the initial binary segmentation. In an embodiment, the method may be applied to all images and in another embodiment, the method may be used for images which comprise a large number of pixels in total or in single dimension and smaller images may not be down-sampled before segmentation.
摘要翻译： 描述了用于分割的二进制图像的上采样方法。 在一个实施例中，在分割之前对数字图像进行下采样。 然后，所得到的具有比原始图像更低分辨率的初始二进制分割被上采样和平滑以产生具有比初始二进制分割更高分辨率的临时非二进制解。 然后基于阈值从临时非二进制解决方案计算图像的最终二进制分割。 该方法不使用原始图像数据从最初的二进制分割推断最终的二进制分割解决方案。 在一个实施例中，该方法可以应用于所有图像，并且在另一个实施例中，该方法可以用于总共或单维度中包含大量像素的图像，并且在分割之前可能不会对较小的图像进行下采样。
-
公开(公告)号：US20120294519A1
公开(公告)日：2012-11-22
申请号：US13108945
申请日：2011-05-16
申请人： Kaiming He , Jian Sun , Carsten Curt Eckard Rother , Xiao-Ou Tang
发明人： Kaiming He , Jian Sun , Carsten Curt Eckard Rother , Xiao-Ou Tang
IPC分类号： G06K9/34
摘要： A computing device is described herein that is configured to select a pixel pair including a foreground pixel of an image and a background pixel of the image from a global set of pixels based at least on spatial distances from an unknown pixel and color distances from the unknown pixel. The computing device is further configured to determine an opacity measure for the unknown pixel based at least on the selected pixel pair.
摘要翻译： 本文描述了一种计算设备，其被配置为至少基于与未知像素的空间距离和来自未知像素的颜色距离从全局像素集合中选择包括图像的前景像素和图像的背景像素的像素对 像素。 计算设备还被配置为至少基于所选择的像素对来确定未知像素的不透明度测量。
-
公开(公告)号：US08971612B2
公开(公告)日：2015-03-03
申请号：US13327273
申请日：2011-12-15
申请人： Jamie Daniel Joseph Shotton , Pushmeet Kohli , Stefan Johannes Josef Holzer , Shahram Izadi , Carsten Curt Eckard Rother , Sebastian Nowozin , David Kim , David Molyneaux , Otmar Hilliges
发明人： Jamie Daniel Joseph Shotton , Pushmeet Kohli , Stefan Johannes Josef Holzer , Shahram Izadi , Carsten Curt Eckard Rother , Sebastian Nowozin , David Kim , David Molyneaux , Otmar Hilliges
CPC分类号： G06K9/6255 , G06K9/6282 , G06T5/00 , G06T7/55 , G06T2207/20081
摘要： Learning image processing tasks from scene reconstructions is described where the tasks may include but are not limited to: image de-noising, image in-painting, optical flow detection, interest point detection. In various embodiments training data is generated from a 2 or higher dimensional reconstruction of a scene and from empirical images of the same scene. In an example a machine learning system learns at least one parameter of a function for performing the image processing task by using the training data. In an example, the machine learning system comprises a random decision forest. In an example, the scene reconstruction is obtained by moving an image capture apparatus in an environment where the image capture apparatus has an associated dense reconstruction and camera tracking system.
摘要翻译： 描述了来自场景重建的学习图像处理任务，其中任务可以包括但不限于：图像去噪，图像在画，光流检测，兴趣点检测。 在各种实施例中，训练数据从场景的2维或更高维度的重构以及相同场景的经验图像生成。 在一个示例中，机器学习系统通过使用训练数据来学习用于执行图像处理任务的功能的至少一个参数。 在一个例子中，机器学习系统包括随机决策树。 在一个示例中，通过在图像捕获装置具有相关密集重建和相机跟踪系统的环境中移动图像捕获装置来获得场景重建。
-
公开(公告)号：US09070047B2
公开(公告)日：2015-06-30
申请号：US13337309
申请日：2011-12-27
申请人： Reinhard Sebastian Bernhard Nowozin , Carsten Curt Eckard Rother , Bangpeng Yao , Toby Leonard Sharp , Pushmeet Kohli
发明人： Reinhard Sebastian Bernhard Nowozin , Carsten Curt Eckard Rother , Bangpeng Yao , Toby Leonard Sharp , Pushmeet Kohli
CPC分类号： G06K9/6282 , G06K9/6256 , G06K9/6296 , G06N99/005
摘要： A tractable model solves certain labeling problems by providing potential functions having arbitrary dependencies upon an observed dataset (e.g., image data). The model uses decision trees corresponding to various factors to map dataset content to a set of parameters used to define the potential functions in the model. Some factors define relationships among multiple variable nodes. When making label predictions on a new dataset, the leaf nodes of the decision tree determine the effective weightings for such potential functions. In this manner, decision trees define non-parametric dependencies and can represent rich, arbitrary functional relationships if sufficient training data is available. Decision trees training is scalable, both in the training set size and by parallelization. Maximum pseudolikelihood learning can provide for joint training of aspects of the model, including feature test selection and ordering, factor weights, and the scope of the interacting variable nodes used in the graph.
摘要翻译： 易于处理的模型通过提供具有任意依赖于观察数据集（例如图像数据）的潜在功能来解决某些标注问题。 该模型使用与各种因素相对应的决策树将数据集内容映射到用于定义模型中潜在功能的一组参数。 一些因素定义了多个变量节点之间的关系。 在对新数据集进行标签预测时，决策树的叶节点决定了这些潜在功能的有效权重。 以这种方式，决策树定义非参数依赖性，并且如果有足够的训练数据可用，则可以表示丰富的，任意的功能关系。 决策树训练是可扩展的，无论是训练集大小还是并行化。 最大伪可能性学习可以提供模型方面的联合训练，包括特征测试选择和排序，因子权重以及图中使用的交互变量节点的范围。
-
公开(公告)号：US08891884B2
公开(公告)日：2014-11-18
申请号：US13337324
申请日：2011-12-27
CPC分类号： G06K9/6219 , G06K9/6296 , G06T7/11 , G06T7/143 , G06T7/162 , G06T2207/20072 , G06T2207/20076 , G06T2207/20081
摘要： A new tractable model solves labeling problems using regression tree fields, which represent non-parametric Gaussian conditional random fields. Regression tree fields are parameterized by non-parametric regression trees, allowing universal specification of interactions between image observations and variables. The new model uses regression trees corresponding to various factors to map dataset content (e.g., image content) to a set of parameters used to define the potential functions in the model. Some factors define relationships among multiple variable nodes. Further, the training of regression trees is scalable, both in the training set size and in the fact that the training can be parallelized. In one implementation, maximum pseudolikelihood learning provides for joint training of various aspects of the model, including feature test selection and ordering (i.e., the structure of the regression trees), parameters of each factor in the graph, and the scope of the interacting variable nodes used in the graph.
摘要翻译： 一种新的易处理模型使用回归树字段解决了标签问题，这些表示非参数高斯条件随机场。 回归树字段由非参数回归树参数化，允许通用规范图像观察和变量之间的相互作用。 新模型使用与各种因素相对应的回归树将数据集内容（例如，图像内容）映射到用于定义模型中的潜在功能的一组参数。 一些因素定义了多个变量节点之间的关系。 此外，回归树的训练是可扩展的，无论是训练集大小还是培训可并行化的事实。 在一个实现中，最大伪随机学习提供了模型各个方面的联合训练，包括特征测试选择和排序（即回归树结构），图中每个因子的参数以及交互变量的范围 图中使用的节点。
-
公开(公告)号：US20130166481A1
公开(公告)日：2013-06-27
申请号：US13337309
申请日：2011-12-27
申请人： Reinhard Sebastian Bernhard Nowozin , Carsten Curt Eckard Rother , Bangpeng Yao , Toby Leonard Sharp , Pushmeet Kohli
发明人： Reinhard Sebastian Bernhard Nowozin , Carsten Curt Eckard Rother , Bangpeng Yao , Toby Leonard Sharp , Pushmeet Kohli
IPC分类号： G06F15/18
CPC分类号： G06K9/6282 , G06K9/6256 , G06K9/6296 , G06N99/005
摘要： A tractable model solves certain labeling problems by providing potential functions having arbitrary dependencies upon an observed dataset (e.g., image data). The model uses decision trees corresponding to various factors to map dataset content to a set of parameters used to define the potential functions in the model. Some factors define relationships among multiple variable nodes. When making label predictions on a new dataset, the leaf nodes of the decision tree determine the effective weightings for such potential functions. In this manner, decision trees define non-parametric dependencies and can represent rich, arbitrary functional relationships if sufficient training data is available. Decision trees training is scalable, both in the training set size and by parallelization. Maximum pseudolikelihood learning can provide for joint training of aspects of the model, including feature test selection and ordering, factor weights, and the scope of the interacting variable nodes used in the graph.
摘要翻译： 易于处理的模型通过提供具有任意依赖于观察数据集（例如图像数据）的潜在功能来解决某些标注问题。 该模型使用与各种因素相对应的决策树将数据集内容映射到用于定义模型中潜在功能的一组参数。 一些因素定义了多个变量节点之间的关系。 在对新数据集进行标签预测时，决策树的叶节点决定了这些潜在功能的有效权重。 以这种方式，决策树定义非参数依赖性，并且如果有足够的训练数据可用，则可以表示丰富的，任意的功能关系。 决策树训练是可扩展的，无论是训练集大小还是并行化。 最大伪可能性学习可以提供模型方面的联合训练，包括特征测试选择和排序，因子权重以及图中使用的交互变量节点的范围。
-
公开(公告)号：US20130163859A1
公开(公告)日：2013-06-27
申请号：US13337324
申请日：2011-12-27
IPC分类号： G06K9/62
CPC分类号： G06K9/6219 , G06K9/6296 , G06T7/11 , G06T7/143 , G06T7/162 , G06T2207/20072 , G06T2207/20076 , G06T2207/20081
摘要： A new tractable model solves labeling problems using regression tree fields, which represent non-parametric Gaussian conditional random fields. Regression tree fields are parameterized by non-parametric regression trees, allowing universal specification of interactions between image observations and variables. The new model uses regression trees corresponding to various factors to map dataset content (e.g., image content) to a set of parameters used to define the potential functions in the model. Some factors define relationships among multiple variable nodes. Further, the training of regression trees is scalable, both in the training set size and in the fact that the training can be parallelized. In one implementation, maximum pseudolikelihood learning provides for joint training of various aspects of the model, including feature test selection and ordering (i.e., the structure of the regression trees), parameters of each factor in the graph, and the scope of the interacting variable nodes used in the graph.
摘要翻译： 一种新的易处理模型使用回归树字段解决了标签问题，这些表示非参数高斯条件随机场。 回归树字段由非参数回归树参数化，允许通用规范图像观察和变量之间的相互作用。 新模型使用与各种因素相对应的回归树将数据集内容（例如，图像内容）映射到用于定义模型中的潜在功能的一组参数。 一些因素定义了多个变量节点之间的关系。 此外，回归树的训练是可扩展的，无论是训练集大小还是培训可并行化的事实。 在一个实现中，最大伪随机学习提供了模型各个方面的联合训练，包括特征测试选择和排序（即回归树结构），图中每个因子的参数以及交互变量的范围 图中使用的节点。
-
-
-
-
-
-
-
-
-
搜索结果
20 条记录 (耗时 0.023 秒)
