公开(公告)号：US07149368B2

公开(公告)日：2006-12-12

申请号：US10299623

申请日：2002-11-19

Applicant: Xin Tong ,  Ligang Liu ,  Baining Guo ,  Heung-Yeung Shum

Inventor： Xin Tong ,  Ligang Liu ,  Baining Guo ,  Heung-Yeung Shum

IPC: G06K9/36

CPC classification number: G06T15/04

Abstract: A bidirectional texture function (BTF) synthesizer serves to synthesize BTFs on arbitrary manifold surfaces using “surface textons” given a sample BTF as an input. The synthesized BTFs fit the surface geometry naturally and seamlessly, and not only look similar to a sample BTF in all viewing and lighting conditions, but also exhibit a consistent mesostructure when the viewing and lighting directions change. Further, the synthesized BTFs capture the fine-scale shadows, occlusions, and specularities caused by surface mesostructures, thereby improving the perceived realism of the textured surfaces. In addition, the BTF synthesizer can describe real-world textures to allow a user to decorate real-world geometry with real-world textures. Finally, BTF synthesis using surface textons works well for any materials that can be described by three-dimensional textons.

Abstract translation: 双向纹理函数（BTF）合成器用于在给定样本BTF作为输入的情况下使用“表面纹理”合成任意歧管表面上的BTF。 合成的BTF自然无缝地适应表面几何，并且在所有观察和照明条件下不仅看起来类似于样品BTF，而且在观察和照明方向改变时也表现出一致的介观结构。 此外，合成的BTF捕获由表面介观结构引起的微小尺度的阴影，遮挡物和镜面反射，从而改善纹理表面的感知现实性。 此外，BTF合成器可以描述真实世界的纹理，以允许用户使用真实世界纹理来装饰真实世界的几何。 最后，使用表面纹理的BTF合成对于可以由三维文本描述的任何材料起作用。

公开(公告)号：US20050280647A1

公开(公告)日：2005-12-22

申请号：US10990142

申请日：2004-11-15

Applicant: Xi Wang ,  Xin Tong ,  Stephen Lin ,  Baining Guo ,  Heung-Yeung Shum

Inventor： Xi Wang ,  Xin Tong ,  Stephen Lin ,  Baining Guo ,  Heung-Yeung Shum

IPC: G06T15/20 ,  G06T15/50 ,  G06T15/60 ,  G06T17/00 ,  G09G5/00

CPC classification number: G06T15/04

Abstract: A “mesostructure renderer” uses pre-computed multi-dimensional “generalized displacement maps” (GDM) to provide real-time rendering of general non-height-field mesostructures on both open and closed surfaces of arbitrary geometry. In general, the GDM represents the distance to solid mesostructure along any ray cast from any point within a volumetric sample. Given the pre-computed GDM, the mesostructure renderer then computes mesostructure visibility jointly in object space and texture space, thereby enabling both control of texture distortion and efficient computation of texture coordinates and shadowing. Further, in one embodiment, the mesostructure renderer uses the GDM to render mesostructures with either local or global illumination as a per-pixel process using conventional computer graphics hardware to accelerate the real-time rendering of the mesostructures. Further acceleration of mesostructure rendering is achieved in another embodiment by automatically reducing the number of triangles in the rendering pipeline according to a user-specified threshold for acceptable texture distortion.

Abstract translation: “mesostructure渲染器”使用预先计算的多维“广义位移图”（GDM），以便在任意几何的开放和闭合表面上提供一般非高度场介观结构的实时渲染。 一般来说，GDM表示沿着体积样品内的任何点的任何射线投射到固体介观结构的距离。 给定预先计算的GDM，然后，介观结构渲染器在对象空间和纹理空间中联合计算介观结构可见度，从而实现纹理失真的控制和纹理坐标和阴影的有效计算。 此外，在一个实施例中，使用传统计算机图形硬件的介面结构渲染器使用GDM来渲染具有局部或全局照明的介观结构作为每像素处理，以加速介观结构的实时渲染。 在另一个实施例中，通过根据用户指定的可接受纹理失真的阈值自动减少渲染流水线中的三角形数量来实现进一步加速的介观结构渲染。

公开(公告)号：US5946414A

公开(公告)日：1999-08-31

申请号：US162119

申请日：1998-08-28

Applicant: Todd A. Cass ,  Xin Tong

Inventor： Todd A. Cass ,  Xin Tong

IPC: H04N1/387 ,  G06T1/00 ,  G06T9/00 ,  H04N1/32 ,  H04N1/41 ,  H04N1/46 ,  H04N1/60 ,  G06K9/00

CPC classification number: G06T9/00 ,  G06T1/0021 ,  H04N1/32208 ,  H04N1/32309 ,  H04N2201/3261 ,  H04N2201/327

Abstract: Message values included in a set of valid message values that constitute a coding scheme are each encoded in an image region, called an encoded signal block, composed of a spatially arranged pattern of colored sub-regions. The colored sub-regions have color values produced by modulating a reference color value by a color change quantity expressed as a color space direction in a multi-dimensional color space such that the average color of all of the sub-region colors is the reference color. There is a unique pattern of color-modulated sub-regions for each valid message value in the coding scheme. In one embodiment, the color space direction is computed to be simultaneously detectable by a digital image capture device such as a scanner and substantially imperceptible to a human viewer, so that the embedded data represented by the pattern of color modulations are visually imperceptible in the encoded signal block. When the reference color is determined to be the average color of an image region in an original color image, the encoded signal block may replace the image region in the original image, producing an encoded image version of the original image having little or no image degradation. In this case, the original image colors become carriers of the encoded data. Signal blocks may be arranged to encode data in only one dimension in an image, which allows for less complex decoding algorithms, or in a two dimensional array or grid-like structure, which allows for a high encoded data density rate.

Abstract translation: 包含在构成编码方案的一组有效消息值中的消息值分别被编码在由彩色子区域的空间排列图案组成的称为编码信号块的图像区域中。 有色子区域具有通过在多维颜色空间中以颜色空间方向表示的颜色变化量调制参考颜色值而产生的颜色值，使得所有子区域颜色的平均颜色为参考颜色 。 对于编码方案中的每个有效消息值，存在着色调制子区域的独特模式。 在一个实施例中，颜色空间方向被计算为可由诸如扫描仪的数字图像捕获设备同时检测，并且对人类观察者基本上不可察觉，使得由编码的颜色调制图案表示的嵌入数据在视觉上不可察觉 信号块。 当参考颜色被确定为原始彩色图像中的图像区域的平均颜色时，编码信号块可以代替原始图像中的图像区域，产生具有很少或没有图像劣化的原始图像的编码图像版本 。 在这种情况下，原始图像颜色成为编码数据的载体。 信号块可以被布置成仅在图像中的一个维度上对数据进行编码，这允许较不复杂的解码算法，或允许高编码数据密度率的二维阵列或网格状结构。

公开(公告)号：US08953037B2

公开(公告)日：2015-02-10

申请号：US13274191

申请日：2011-10-14

Applicant: Jiaping Wang ,  Baining Guo ,  Peiran Ren ,  John Michael Snyder ,  Xin Tong

Inventor： Jiaping Wang ,  Baining Guo ,  Peiran Ren ,  John Michael Snyder ,  Xin Tong

IPC: H04N9/47 ,  H04N1/00 ,  G01N21/55

CPC classification number: H04N1/00018 ,  G01N21/55 ,  H04N1/00013 ,  H04N1/00045 ,  H04N1/00087

Abstract: A system for reflectance acquisition of a target includes a light source, an image capture device, and a reflectance reference chart. The reflectance reference chart is fixed relative to the target. The light source provides a uniform band of light across at least a dimension of the target. The image capture device is configured and positioned to encompass at least a portion of the target and at least a portion of the reflectance reference chart within a field-of-view of the image capture device. The image capture device captures a sequence of images of the target and the reflectance reference chart during a scan thereof. Reflectance responses are calculated for the pixels in the sequence of images. Reference reflectance response distribution functions are matched to the calculated reflectance responses, and an image of the target is reconstructed based at least in part on the matched reference reflectance response distribution functions.

Abstract translation: 用于目标的反射获取的系统包括光源，图像捕获装置和反射率参考图。 反射率参考图表相对于目标是固定的。 光源在目标的至少一维上提供均匀的光束。 图像捕获设备被配置和定位成在图像捕获设备的视野内包围目标的至少一部分和反射参考图的至少一部分。 图像捕获装置在其扫描期间捕获目标的图像序列和反射率参考图。 针对图像序列中的像素计算反射响应。 参考反射响应分布函数与所计算的反射率响应匹配，并且至少部分地基于匹配的参考反射响应分布函数来重建目标的图像。

公开(公告)号：US08830092B2

公开(公告)日：2014-09-09

申请号：US13156610

申请日：2011-06-09

Applicant: Jim Normile ,  Thomas Pun ,  Xiaojin Shi ,  Xin Tong ,  Hsi-Jung Wu

Inventor： Jim Normile ,  Thomas Pun ,  Xiaojin Shi ,  Xin Tong ,  Hsi-Jung Wu

IPC: H03M7/00

CPC classification number: H04N19/154 ,  H04N19/156 ,  H04N19/164

Abstract: Techniques for encoding data based at least in part upon an awareness of the decoding complexity of the encoded data and the ability of a target decoder to decode the encoded data are disclosed. In some embodiments, a set of data is encoded based at least in part upon a state of a target decoder to which the encoded set of data is to be provided. In some embodiments, a set of data is encoded based at least in part upon the states of multiple decoders to which the encoded set of data is to be provided.

Abstract translation: 公开了至少部分地基于编码数据的解码复杂度的意识和目标解码器解码编码数据的能力对数据进行编码的技术。 在一些实施例中，至少部分地基于要提供编码数据集合的目标解码器的状态对数据集进行编码。 在一些实施例中，一组数据至少部分地基于要提供编码数据集的多个解码器的状态进行编码。

公开(公告)号：US08811475B2

公开(公告)日：2014-08-19

申请号：US13437931

申请日：2012-04-03

Applicant: Xin Tong ,  Hsi Jung Wu ,  Thomas Pun ,  Adriana Dumitras ,  Barin Geoffry Haskell ,  Jim Normile

Inventor： Xin Tong ,  Hsi Jung Wu ,  Thomas Pun ,  Adriana Dumitras ,  Barin Geoffry Haskell ,  Jim Normile

IPC: H04N7/12 ,  H04N7/26

CPC classification number: H04N19/00193 ,  H04N19/00 ,  H04N19/152 ,  H04N19/194

Abstract: A method of encoding a sequence of video images is described. The method receives the sequence of video images. The method iteratively examines different encoding solutions for the sequence of video images to identify an encoding solution that optimizes image quality while meeting a target bit rate and satisfying a set of constraints regarding flow of encoded data through an input buffer of a hypothetical reference decoder for decoding the encoded video sequence. The iterative examining includes, for each encoding solution, determining whether the hypothetical reference decoder underflows while processing the encoding solution for any set of images within the video sequence.

Abstract translation: 描述了对视频图像序列进行编码的方法。 该方法接收视频图像序列。 该方法迭代地检查视频图像序列的不同编码解决方案，以识别优化图像质量同时满足目标比特率并且通过用于解码的假设参考解码器的输入缓冲器满足编码数据流的一组约束的编码解决方案 编码视频序列。 对于每个编码解决方案，迭代检查包括在处理视频序列内的任何图像集合的编码解决方案的同时确定假想参考解码器是否下溢。

公开(公告)号：US08737825B2

公开(公告)日：2014-05-27

申请号：US12781813

申请日：2010-05-17

Applicant: Paul Towner ,  Courtney Kennedy ,  Randy Ubillos ,  Greg Mullins ,  Greg Wallace ,  Peter Chou ,  Xin Tong

Inventor： Paul Towner ,  Courtney Kennedy ,  Randy Ubillos ,  Greg Mullins ,  Greg Wallace ,  Peter Chou ,  Xin Tong

IPC: H04N5/93

CPC classification number: H04N7/0117 ,  G11B27/00 ,  H04N5/765 ,  H04N5/917 ,  H04N19/107 ,  H04N19/11 ,  H04N19/12 ,  H04N19/162 ,  H04N19/174 ,  H04N19/176 ,  H04N19/59

Abstract: Some embodiments provide a video recording device for capturing a video clip. The video recording device receives a selection of a non-temporally compressed encoding scheme from several different encoding schemes for encoding the video clip. The different encoding schemes include at least one temporally compressed encoding scheme and at least the selected non-temporally compressed encoding scheme. The video recording device captures the video clip as several frames. The video recording device non-temporally encodes each of the frames as several slices. The slices of a particular frame are for decoding by several processing units of a video decoding device. The video recording device stores the video clip in a storage.

Abstract translation: 一些实施例提供用于捕获视频剪辑的视频记录装置。 视频记录设备从用于编码视频剪辑的几种不同的编码方案中接收非时间压缩编码方案的选择。 不同的编码方案包括至少一个时间压缩编码方案和至少所选择的非时间压缩编码方案。 视频记录设备将视频剪辑捕获为几帧。 视频记录设备将每个帧非时间编码为几个片。 特定帧的片段用于由视频解码装置的多个处理单元进行解码。 视频记录装置将视频剪辑存储在存储器中。

公开(公告)号：US08698829B2

公开(公告)日：2014-04-15

申请号：US12789876

申请日：2010-05-28

Applicant: Li-Yi Wei ,  Chongyang Ma ,  Xin Tong

Inventor： Li-Yi Wei ,  Chongyang Ma ,  Xin Tong

IPC: G09G5/00

CPC classification number: G06T11/001

Abstract: Output textures may be generated by synthesizing an input texture comprising discrete elements with a set of boundary conditions. Elements of the input texture are copied from the input texture to an output texture that is defined by a set of boundary conditions and are then refined. The elements of the output texture are refined by assigning domain and/or attribute information to the elements of the output texture element by minimizing an energy function measuring a similarity between output neighborhoods of the output texture and a corresponding best matching input neighborhood of the input texture.

Abstract translation: 输出纹理可以通过合成包括具有一组边界条件的离散元素的输入纹理来生成。 将输入纹理的元素从输入纹理复制到由一组边界条件定义的输出纹理，然后进行细化。 通过最小化测量输出纹理的输出邻域与输入纹理的相应最佳匹配输入邻域之间的相似性的能量函数，将域和/或属性信息分配给输出纹理元素的元素，从而细化输出纹理的元素 。

公开(公告)号：US20130342527A1

公开(公告)日：2013-12-26

申请号：US13585540

申请日：2012-08-14

Applicant: David Molyneaux ,  Xin Tong ,  Zicheng Liu ,  Eric Chang ,  Fan Yang ,  Jay Kapur ,  Emily Yang ,  Yang Liu ,  Hsiang-Tao Wu

Inventor： David Molyneaux ,  Xin Tong ,  Zicheng Liu ,  Eric Chang ,  Fan Yang ,  Jay Kapur ,  Emily Yang ,  Yang Liu ,  Hsiang-Tao Wu

IPC: G06T13/00 ,  G06T15/00

CPC classification number: G06T7/0032 ,  A63F13/213 ,  A63F13/655 ,  G06K9/00214 ,  G06K9/00369 ,  G06K9/469 ,  G06K9/6206 ,  G06K9/6211 ,  G06T7/344 ,  G06T13/40 ,  G06T17/20 ,  G06T2207/10028

Abstract: A method for constructing an avatar of a human subject includes acquiring a depth map of the subject, obtaining a virtual skeleton of the subject based on the depth map, and harvesting from the virtual skeleton a set of characteristic metrics. Such metrics correspond to distances between predetermined points of the virtual skeleton. In this example method, the characteristic metrics are provided as input to an algorithm trained using machine learning. The algorithm may be trained using a human model in a range of poses, and a range of human models in a single pose, to output a virtual body mesh as a function of the characteristic metrics. The method also includes constructing a virtual head mesh distinct from the virtual body mesh, with facial features resembling those of the subject, and connecting the virtual body mesh to the virtual head mesh.

Abstract translation: 用于构建人类对象的化身的方法包括获取对象的深度图，基于深度图获取对象的虚拟骨架，以及从虚拟骨架获取一组特征度量。 这样的度量对应于虚拟骨架的预定点之间的距离。 在该示例方法中，特征度量被提供作为使用机器学习训练的算法的输入。 可以使用姿态范围中的人类模型和单个姿态中的人类模型的范围来训练算法，以根据特征度量输出虚拟身体网格。 该方法还包括构建与虚拟身体网格不同的虚拟头部网格，以及类似于对象的面部特征，以及将虚拟身体网格物体连接到虚拟头部网格物体。

公开(公告)号：US08570522B2

公开(公告)日：2013-10-29

申请号：US13538558

申请日：2012-06-29

Applicant: Jiaping Wang ,  Moshe Benezra ,  Xin Tong ,  John Michael Snyder ,  Baining Guo

Inventor： Jiaping Wang ,  Moshe Benezra ,  Xin Tong ,  John Michael Snyder ,  Baining Guo

IPC: G01N21/55

CPC classification number: G01N21/55

Abstract: A mechanism is disclosed for capturing reflected rays from a surface. A first and second lens aligned along a same optical center axis are configured so that a beam of light collimated parallel to the lens center axis directed to a first side, is converged toward the lens center axis on a second side. A first light beam source between the first and second lenses directs a light beam toward the first lens parallel to the optical center axis. Second light beam source(s) on the second side of the first lens, direct a light beam toward a focal plane of the first lens at a desired angle. An image capturing component, at the second side of the second lens, has an image capture surface directed toward the second lens to capture images of the light reflected from a sample capture surface at the focal plane of the first lens.

Abstract translation: 公开了用于从表面捕获反射光线的机构。 沿着相同的光学中心轴对准的第一和第二透镜被配置为使得平行于指向第一侧的透镜中心轴准直的光束在第二侧上朝向透镜中心轴会聚。 第一和第二透镜之间的第一光束源将平行于光学中心轴的光束朝着第一透镜引导。 在第一透镜的第二侧上的第二光束源将光束以期望的角度引导到第一透镜的焦平面。 在第二透镜的第二侧的图像捕获部件具有指向第二透镜的图像捕获表面，以捕获在第一透镜的焦平面处从样品捕获表面反射的光的图像。