公开(公告)号：US08798357B2

公开(公告)日：2014-08-05

申请号：US13544817

申请日：2012-07-09

Applicant: Sudipta N Sinha ,  Hyon Lim ,  Michael Cohen ,  Matt Uyttendaele

Inventor： Sudipta N Sinha ,  Hyon Lim ,  Michael Cohen ,  Matt Uyttendaele

IPC: G06K9/00

CPC classification number: G06K9/46 ,  G06K9/00664 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/20016 ,  G06T2207/30244

Abstract: Image-based localization technique embodiments are presented which provide a real-time approach for image-based video camera localization within large scenes that have been reconstructed offline using structure from motion or similar techniques. From monocular video, a precise 3D position and 3D orientation of the camera can be estimated on a frame by frame basis using only visual features.

Abstract translation: 提出了基于图像的定位技术实施例，其提供了使用已经使用运动或类似技术的结构离线重建的大场景内基于图像的摄像机定位的实时方法。 从单眼视频，可以使用仅视觉特征逐帧估计摄像机的精确3D位置和3D取向。

公开(公告)号：US08547389B2

公开(公告)日：2013-10-01

申请号：US12754530

申请日：2010-04-05

Applicant: Hugues Hoppe ,  Charles Han ,  Matt Uyttendaele

Inventor： Hugues Hoppe ,  Charles Han ,  Matt Uyttendaele

IPC: G09G5/00 ,  G09G5/02 ,  H04N5/46 ,  H04N5/445 ,  H04N9/74 ,  H04N1/46 ,  H04N1/393 ,  G03F3/08 ,  G06K9/00 ,  G06K9/40 ,  G06K9/36 ,  G06K9/32

CPC classification number: G06T5/50 ,  G06T11/001 ,  G06T17/05 ,  G06T2207/10024 ,  G06T2207/10032 ,  G06T2207/20016

Abstract: Embodiments are described for a method to generate an image that includes image structure detail captured from a first image and color from a second image. The first image of a defined subject can be obtained from a computer memory. The first image may be a downsampled fine image with image detail. The second image captured of the defined subject in the first image can be obtained from a computer memory. The second image may be a coarse image. A target pixel in the second image can be selected. A target color distribution for a pixel window of the target pixel can then be computed. A source color distribution for a pixel window of a corresponding pixel in the first image can be computed using a computer processor. Further, a statistic of the target pixel can be determined with respect to the target color distribution. The source color in the source color distribution can be computed with the statistic. The target pixel color can then be replaced by the source color.

Abstract translation: 描述了用于生成包括从第一图像捕获的图像结构细节和来自第二图像的颜色的图像的方法的实施例。 可以从计算机存储器获得定义的主题的第一图像。 第一个图像可能是具有图像细节的下采样的精细图像。 可以从计算机存储器获得在第一图像中捕获的定义的对象的第二图像。 第二图像可以是粗图像。 可以选择第二图像中的目标像素。 然后可以计算目标像素的像素窗口的目标颜色分布。 可以使用计算机处理器来计算第一图像中相应像素的像素窗口的源颜色分布。 此外，可以相对于目标颜色分布来确定目标像素的统计量。 源颜色分布中的源颜色可以用统计量计算。 然后可以用源颜色替换目标像素颜色。

公开(公告)号：US08340415B2

公开(公告)日：2012-12-25

申请号：US12754526

申请日：2010-04-05

Applicant: Hugues Hoppe ,  Charles Han ,  Matt Uyttendaele

Inventor： Hugues Hoppe ,  Charles Han ,  Matt Uyttendaele

IPC: G06K9/00

CPC classification number: G06T3/4007 ,  G06T7/90 ,  G06T2207/20016 ,  G06T2207/20212

Abstract: Embodiments are described for a system and method for generating a multi-resolution image pyramid. The method can include obtaining an image captured as a coarse image of a defined subject and a fine image of the defined subject. The fine image can be downsampled to create a temporary image. A further operation is applying a structure transfer operation to the temporary image to transfer color detail from the coarse image. The structure transfer takes place while retaining structural detail from the temporary image. A blending operation can be applied between the temporary image and the fine image to construct an intermediate image for at least one intermediate level in the multi-resolution image pyramid between the fine image and the coarse image.

Abstract translation: 针对用于生成多分辨率图像金字塔的系统和方法描述了实施例。 该方法可以包括获得作为所定义的对象的粗略图像捕获的图像和所定义的对象的精细图像。 可以对精细图像进行下采样以创建临时图像。 进一步的操作是将结构传递操作应用于临时图像以从粗略图像传送颜色细节。 结构转移发生在从临时图像中保留结构细节的同时， 可以在临时图像和精细图像之间应用混合操作，以在精细图像和粗略图像之间的多分辨率图像金字塔中构建用于至少一个中间水平的中间图像。

公开(公告)号：US20110243438A1

公开(公告)日：2011-10-06

申请号：US12754526

申请日：2010-04-05

Applicant: Hugues Hoppe ,  Charles Han ,  Matt Uyttendaele

Inventor： Hugues Hoppe ,  Charles Han ,  Matt Uyttendaele

IPC: G06K9/00

CPC classification number: G06T3/4007 ,  G06T7/90 ,  G06T2207/20016 ,  G06T2207/20212

Abstract: Embodiments are described for a system and method for generating a multi-resolution image pyramid. The method can include obtaining an image captured as a coarse image of a defined subject and a fine image of the defined subject. The fine image can be downsampled to create a temporary image. A further operation is applying a structure transfer operation to the temporary image to transfer color detail from the coarse image. The structure transfer takes place while retaining structural detail from the temporary image. A blending operation can be applied between the temporary image and the fine image to construct an intermediate image for at least one intermediate level in the multi-resolution image pyramid between the fine image and the coarse image.

Abstract translation: 针对用于生成多分辨率图像金字塔的系统和方法描述了实施例。 该方法可以包括获得作为所定义的对象的粗略图像捕获的图像和所定义的对象的精细图像。 可以对精细图像进行下采样以创建临时图像。 进一步的操作是将结构传递操作应用于临时图像以从粗略图像传送颜色细节。 结构转移发生在从临时图像中保留结构细节的同时， 可以在临时图像和精细图像之间应用混合操作，以在精细图像和粗略图像之间的多分辨率图像金字塔中构建用于至少一个中间水平的中间图像。

公开(公告)号：US20110242126A1

公开(公告)日：2011-10-06

申请号：US12754530

申请日：2010-04-05

Applicant: Hugues Hoppe ,  Charles Han ,  Matt Uyttendaele

Inventor： Hugues Hoppe ,  Charles Han ,  Matt Uyttendaele

IPC: G09G5/02

CPC classification number: G06T5/50 ,  G06T11/001 ,  G06T17/05 ,  G06T2207/10024 ,  G06T2207/10032 ,  G06T2207/20016

Abstract: Embodiments are described for a method to generate an image that includes image structure detail captured from a first image and color from a second image. The first image of a defined subject can be obtained from a computer memory. The first image may be a downsampled fine image with image detail. The second image captured of the defined subject in the first image can be obtained from a computer memory. The second image may be a coarse image. A target pixel in the second image can be selected. A target color distribution for a pixel window of the target pixel can then be computed. A source color distribution for a pixel window of a corresponding pixel in the first image can be computed using a computer processor. Further, a statistic of the target pixel can be determined with respect to the target color distribution. The source color in the source color distribution can be computed with the statistic. The target pixel color can then be replaced by the source color.

Abstract translation: 描述了用于生成包括从第一图像捕获的图像结构细节和来自第二图像的颜色的图像的方法的实施例。 可以从计算机存储器获得定义的主题的第一图像。 第一个图像可能是具有图像细节的下采样的精细图像。 可以从计算机存储器获得在第一图像中捕获的定义的对象的第二图像。 第二图像可以是粗图像。 可以选择第二图像中的目标像素。 然后可以计算目标像素的像素窗口的目标颜色分布。 可以使用计算机处理器来计算第一图像中相应像素的像素窗口的源颜色分布。 此外，可以相对于目标颜色分布来确定目标像素的统计量。 源颜色分布中的源颜色可以用统计量计算。 然后可以用源颜色替换目标像素颜色。

公开(公告)号：US20140010407A1

公开(公告)日：2014-01-09

申请号：US13544817

申请日：2012-07-09

Applicant: Sudipta N Sinha ,  Hyon Lim ,  Michael Cohen ,  Matt Uyttendaele

Inventor： Sudipta N Sinha ,  Hyon Lim ,  Michael Cohen ,  Matt Uyttendaele

IPC: G06K9/46

CPC classification number: G06K9/46 ,  G06K9/00664 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/20016 ,  G06T2207/30244

Abstract: Image-based localization technique embodiments are presented which provide a real-time approach for image-based video camera localization within large scenes that have been reconstructed offline using structure from motion or similar techniques. From monocular video, a precise 3D position and 3D orientation of the camera can be estimated on a frame by frame basis using only visual features.

Abstract translation: 提出了基于图像的定位技术实施例，其提供了使用已经使用运动或类似技术的结构离线重建的大场景内基于图像的摄像机定位的实时方法。 从单眼视频，可以使用仅视觉特征逐帧估计摄像机的精确3D位置和3D取向。