公开(公告)号：US6016148A

公开(公告)日：2000-01-18

申请号：US870480

申请日：1997-06-06

Applicant: Sing Bing Kang ,  Keith Waters

Inventor： Sing Bing Kang ,  Keith Waters

IPC: G06T15/04 ,  G06T15/70 ,  G06T11/60 ,  G06T17/20

CPC classification number: G06T15/04

Abstract: A method for mapping a digitized image of a face to a wireframe is provided. The wireframe is composed of a plurality of nodes connected by lines. The method includes the steps of detecting a plurality of facial features from the plurality of pixels of a reference facial image. Corresponding facial landmark nodes in the wireframe topology are determined. A transform between the facial features and the landmark nodes is computed to map the wireframe topology to reference facial image. The reference facial image and a target facial image are cropped using a bounding box. The cropped reference facial image is registered with the cropped target facial image to determine a displacement field. The displacement field is applied to the mapped wireframe topology for the reference facial image to map the target facial image to the wireframe topology.

Abstract translation: 提供了将面部的数字化图像映射到线框的方法。 线框由通过线连接的多个节点组成。 该方法包括从参考面部图像的多个像素中检测多个面部特征的步骤。 确定线框拓扑中的相应的面部标记节点。 计算面部特征和地标节点之间的变换，以将线框拓扑映射到参考面部图像。 使用边界框裁剪参考面部图像和目标面部图像。 裁剪的参考面部图像与裁剪的目标面部图像一起登记，以确定位移场。 将位移场应用于参考面部图像的映射线框拓扑，以将目标面部图像映射到线框拓扑。

公开(公告)号：US09881354B2

公开(公告)日：2018-01-30

申请号：US13421307

申请日：2012-03-15

Applicant: Johannes Peter Kopf ,  Sing Bing Kang ,  Wolf Kienzle ,  Steven M. Drucker

Inventor： Johannes Peter Kopf ,  Sing Bing Kang ,  Wolf Kienzle ,  Steven M. Drucker

IPC: G06K9/00 ,  G06T3/40 ,  G06T5/00

CPC classification number: G06T3/4038 ,  G06T5/005

Abstract: Described is a technology by which an image such as a stitched panorama is automatically cropped based upon predicted quality data with respect to filling missing pixels. The image may be completed, including by completing only those missing pixels that remain after cropping. Predicting quality data may be based on using restricted search spaces corresponding to the missing pixels. The crop is computed based upon the quality data, in which the crop is biased towards including original pixels and excluding predicted low quality pixels. Missing pixels are completed by using restricted search spaces to find replacement values for the missing pixels, and may use histogram matching for texture synthesis.

公开(公告)号：US08750645B2

公开(公告)日：2014-06-10

申请号：US12634699

申请日：2009-12-10

Applicant: Neel Suresh Joshi ,  Sing Bing Kang ,  Michael F. Cohen ,  Kalyan Krishna Sunkavalli

Inventor： Neel Suresh Joshi ,  Sing Bing Kang ,  Michael F. Cohen ,  Kalyan Krishna Sunkavalli

IPC: G06K9/32 ,  G06K9/36

CPC classification number: H04N5/23232 ,  G06T3/4038 ,  H04N5/23267 ,  H04N5/262

Abstract: A method described herein includes acts of receiving a sequence of images of a scene and receiving an indication of a reference image in the sequence of images. The method further includes an act of automatically assigning one or more weights independently to each pixel in each image in the sequence of images of the scene. Additionally, the method includes an act of automatically generating a composite image based at least in part upon the one or more weights assigned to each pixel in each image in the sequence of images of the scene.

Abstract translation: 本文描述的方法包括接收场景的图像序列并接收图像序列中的参考图像的指示的动作。 该方法还包括自动地将一个或多个权重自动分配给场景图像序列中的每个图像中的每个像素的动作。 此外，该方法包括至少部分地基于分配给场景的图像序列中的每个图像中的每个像素的一个或多个权重来自动生成合成图像的动作。

公开(公告)号：US08548269B2

公开(公告)日：2013-10-01

申请号：US12971840

申请日：2010-12-17

Applicant: Habib Zargarpour ,  Ben Vaught ,  Sing Bing Kang ,  Michael Rondinelli

Inventor： Habib Zargarpour ,  Ben Vaught ,  Sing Bing Kang ,  Michael Rondinelli

IPC: G06K9/36 ,  G06K9/32

CPC classification number: G03B37/04 ,  G03B35/08 ,  G03B37/06 ,  H04N5/23238 ,  H04N13/243

Abstract: A method is disclosed for stitching together first and second sets of images from three or more image sensors. The first set of images are combined into a composite left view of the panorama, and the second set of images are combined into a composite right view of the panorama. When properly stitched together, the left and right views may be presented as a stereoscopic view of the panorama. A stitching algorithm is applied which removes any disparity due to the parallax in the combined left images and in the combined right images.

Abstract translation: 公开了一种用于将来自三个或更多个图像传感器的第一和第二组图像拼接在一起的方法。 第一组图像被组合成全景图的复合左视图，并且第二组图像被组合成全景图的复合右视图。 当正确缝合在一起时，左视图和右视图可以呈现为全景的立体视图。 应用缝合算法，其消除由于组合的左图像和组合的右图像中的视差引起的任何视差。

公开(公告)号：US08526728B2

公开(公告)日：2013-09-03

申请号：US12973922

申请日：2010-12-21

Applicant: Sing Bing Kang ,  Ashish Kapoor ,  Juan Caicedo Rueda

Inventor： Sing Bing Kang ,  Ashish Kapoor ,  Juan Caicedo Rueda

IPC: G06K9/00

CPC classification number: G06T5/00 ,  G06T2207/20092

Abstract: An image enhancement system may match images to a matrix having various enhancements of images for groups of users. The matrix may define image enhancement settings for the particular images and groups of users, and the matching may apply enhancements to a new image that closely matches a user's preferences. After the matrix is initially populated, new users and new images may be added to increase the matrix's accuracy. The image enhancement system may be deployed as a cloud service, where images may be enhanced as a standalone application or as part of a social network or image sharing website. In some embodiments, the image enhancement system may be deployed on a personal computer or as a component of an image capture device.

Abstract translation: 图像增强系统可将图像与具有用户组的各种图像增强的矩阵相匹配。 矩阵可以为特定图像和用户组定义图像增强设置，并且匹配可以对与用户偏好紧密匹配的新图像应用增强。 在最初填充矩阵之后，可以添加新的用户和新的图像以增加矩阵的准确度。 图像增强系统可以部署为云服务，其中可以将图像作为独立应用或作为社交网络或图像共享网站的一部分而增强。 在一些实施例中，图像增强系统可以部署在个人计算机上或作为图像捕获设备的组件。

公开(公告)号：US20120155786A1

公开(公告)日：2012-06-21

申请号：US12971840

申请日：2010-12-17

Applicant: Habib Zargarpour ,  Ben Vaught ,  Sing Bing Kang ,  Michael Rondinelli

Inventor： Habib Zargarpour ,  Ben Vaught ,  Sing Bing Kang ,  Michael Rondinelli

IPC: G06K9/36

CPC classification number: G03B37/04 ,  G03B35/08 ,  G03B37/06 ,  H04N5/23238 ,  H04N13/243

Abstract: A method is disclosed for stitching together first and second sets of images from three or more image sensors. The first set of images are combined into a composite left view of the panorama, and the second set of images are combined into a composite right view of the panorama. When properly stitched together, the left and right views may be presented as a stereoscopic view of the panorama. A stitching algorithm is applied which removes any disparity due to the parallax in the combined left images and in the combined right images.

Abstract translation: 公开了一种用于将来自三个或更多个图像传感器的第一和第二组图像拼接在一起的方法。 第一组图像被组合成全景图的复合左视图，并且第二组图像被组合成全景图的复合右视图。 当正确缝合在一起时，左视图和右视图可以呈现为全景的立体视图。 应用缝合算法，其消除由于组合的左图像和组合的右图像中的视差引起的任何视差。

公开(公告)号：US20120154518A1

公开(公告)日：2012-06-21

申请号：US12971580

申请日：2010-12-17

Applicant: Habib Zargarpour ,  Alex Garden ,  Ben Vaught ,  Sing Bing Kang ,  Michael Rondinelli

Inventor： Habib Zargarpour ,  Alex Garden ,  Ben Vaught ,  Sing Bing Kang ,  Michael Rondinelli

IPC: H04N7/00

CPC classification number: G03B37/06 ,  G03B17/565 ,  G03B35/08 ,  G03B37/04 ,  H04N13/243 ,  H04N13/282 ,  H04N2213/001

Abstract: Systems and methods are disclosed for generating panoramic stereoscopic images. The system includes an assembly of three or more catadioptric image sensors affixed to each other in a chassis. Each image sensor generates a catadioptric image of a panorama, which may for example be a 360° view of a scene. The software components process the catadioptric image to a 3D stereoscopic view of a panorama.

Abstract translation: 公开了用于产生全景立体图像的系统和方法。 该系统包括在底盘中彼此固定的三个或更多个折反射图像传感器的组件。 每个图像传感器产生全景的反射折射图像，其可以例如是场景的360°视图。 软件组件将反射折射图像处理成全景的3D立体视图。

公开(公告)号：US08098728B2

公开(公告)日：2012-01-17

申请号：US11182144

申请日：2005-07-15

Applicant: Simon Winder ,  Matthew Uyttendaele ,  Charles Zitnick, III ,  Richard Szeliski ,  Sing Bing Kang

Inventor： Simon Winder ,  Matthew Uyttendaele ,  Charles Zitnick, III ,  Richard Szeliski ,  Sing Bing Kang

IPC: H04B1/66 ,  H04N7/12 ,  H04N11/02 ,  H04N11/04

CPC classification number: H04N21/4347 ,  H04N13/111 ,  H04N19/109 ,  H04N19/39 ,  H04N19/593 ,  H04N19/597 ,  H04N19/61 ,  H04N19/70 ,  H04N19/96 ,  H04N21/2365

Abstract: A process for compressing and decompressing non-keyframes in sequential sets of contemporaneous video frames making up multiple video streams where the video frames in a set depict substantially the same scene from different viewpoints. Each set of contemporaneous video frames has a plurality frames designated as keyframes with the remaining being non-keyframes. In one embodiment, the non-keyframes are compressed using a multi-directional spatial prediction technique. In another embodiment, the non-keyframes of each set of contemporaneous video frames are compressed using a combined chaining and spatial prediction compression technique. The spatial prediction compression technique employed can be a single direction technique where just one reference frame, and so one chain, is used to predict each non-keyframe, or it can be a multi-directional technique where two or more reference frames, and so chains, are used to predict each non-keyframe.

Abstract translation: 一种用于在构成多个视频流的同步视频帧的顺序集合中压缩和解压缩非关键帧的过程，其中集合中的视频帧从不同视点描绘基本相同的场景。 每组同时期的视频帧具有指定为关键帧的多个帧，其余的是非关键帧。 在一个实施例中，使用多方向空间预测技术来压缩非关键帧。 在另一个实施例中，使用组合链接和空间预测压缩技术来压缩每组同时期视频帧的非关键帧。 所使用的空间预测压缩技术可以是单向技术，其中仅使用一个参考帧，因此使用一条链来预测每个非关键帧，或者它可以是多方向技术，其中两个或更多个参考帧等 链，用于预测每个非关键帧。

公开(公告)号：US20100318914A1

公开(公告)日：2010-12-16

申请号：US12485179

申请日：2009-06-16

Applicant: Charles Lawrence Zitnick, III ,  Bryan K. Ressler ,  Sing Bing Kang ,  Michael F. Cohen ,  Jagannatha Koppal

Inventor： Charles Lawrence Zitnick, III ,  Bryan K. Ressler ,  Sing Bing Kang ,  Michael F. Cohen ,  Jagannatha Koppal

IPC: G06F3/048

CPC classification number: G11B27/034 ,  G11B27/34 ,  H04N21/4854 ,  H04N21/6377 ,  H04N21/658

Abstract: Described is a user interface that displays a representation of a stereo scene, and includes interactive mechanisms for changing parameter values that determine the perceived appearance of that scene. The scene is modeled as if viewed from above, including a representation of a viewer's eyes, a representation of a viewing screen, and an indication simulating what each of the viewer eyes perceives on the viewing screen. Variable parameters may include a vergence parameter, a dolly parameter, a field-of-view parameter, an interocular parameter and a proscenium arch parameter.

Abstract translation: 描述了显示立体场景的表示的用户界面，并且包括用于改变确定该场景的感知外观的参数值的交互机制。 该场景被建模为仿佛从上方观看，包括观看者的眼睛的表示，观看屏幕的表示，以及模拟观看者眼睛在观看屏幕上感知的每一个的指示。 可变参数可以包括聚集参数，小车参数，视野参数，眼镜参数和前景拱参数。

公开(公告)号：US07705876B2

公开(公告)日：2010-04-27

申请号：US10948533

申请日：2004-09-23

Applicant: Gary K. Starkweather ,  Michael J. Sinclair ,  Sing Bing Kang

Inventor： Gary K. Starkweather ,  Michael J. Sinclair ,  Sing Bing Kang

IPC: H04N13/04

CPC classification number: H04N13/376 ,  H04N13/302 ,  H04N13/371 ,  H04N13/378 ,  H04N13/38 ,  H04N13/383

Abstract: Stereoscopic image display is described. In an embodiment, a location of the eye pupils of a viewer is determined and tracked. An image is displayed within a first focus for viewing with the left eye of the viewer, and the image is displayed within a second focus for viewing with the right eye of the viewer. A positional change of the eye pupils is tracked and a sequential image that corresponds to the positional change of the eye pupils is generated for stereoscopic viewing. In another embodiment, an image is displayed for stereoscopic viewing and a head position of a viewer relative to a center of the displayed image is determined. A positional change of the viewer's head is tracked, and a sequential image that corresponds to the positional change of the viewer's head is generated for stereoscopic viewing.

Abstract translation: 描述立体图像显示。 在一个实施例中，确定并跟踪观看者的眼睛瞳孔的位置。 在第一焦点内显示图像以用观看者的左眼观看，并且在第二焦点内显示图像以用观看者的右眼观看。 跟踪眼睛瞳孔的位置变化，并且生成对应于眼睛瞳孔的位置变化的顺序图像用于立体观看。 在另一个实施例中，显示用于立体观看的图像，并且确定观看者相对于所显示图像的中心的头部位置。 跟踪观众头部的位置变化，生成与观众头部的位置变化相对应的顺序图像，用于立体观看。