会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明授权
    • Reconstruction of sparse data
    • 重建稀疏数据
    • US08737769B2
    • 2014-05-27
    • US12954843
    • 2010-11-26
    • Mark FinchJohn SnyderHugues HoppeYonatan Wexler
    • Mark FinchJohn SnyderHugues HoppeYonatan Wexler
    • G06K9/32G06K9/40
    • G06T17/00G06T7/50
    • A dense guide image or signal is used to inform the reconstruction of a target image from a sparse set of target points. The guide image and the set of target points are assumed to be derived from a same real world subject or scene. Potential discontinuities (e.g., tears, edges, gaps, etc.) are first detected in the guide image. The potential discontinuities may be borders of Voronoi regions, perhaps computed using a distance in data space (e.g., color space). The discontinuities and sparse set of points are used to reconstruct the target image. Specifically, pixels of the target image may be interpolated smoothly between neighboring target points, but where neighboring target points are separated by a discontinuity, the interpolation may jump abruptly (e.g., by adjusting or influencing relaxation) at the discontinuity. The target points may be used to select only a subset of the discontinuities to be used during reconstruction.
    • 使用密集的引导图像或信号来通知来自稀疏目标点集合的目标图像的重建。 引导图像和目标点集合被假定为从相同的现实主题或场景导出。 在引导图像中首先检测到潜在的不连续性(例如,泪液,边缘,间隙等)。 潜在的不连续性可以是Voronoi区域的边界,可以使用数据空间中的距离(例如,颜色空间)来计算。 不连续点和稀疏集合点用于重建目标图像。 具体地说,目标图像的像素可以在相邻目标点之间平滑地内插,但是当相邻目标点被不连续分开时,插值可能突然地跳跃(例如,通过调节或影响松弛)而跳跃。 目标点可以用于仅在重建期间仅选择要使用的不连续的子集。
    • 2. 发明申请
    • RECONSTRUCTION OF SPARSE DATA
    • 重新建立稀疏数据
    • US20120134597A1
    • 2012-05-31
    • US12954843
    • 2010-11-26
    • Mark FinchJohn SnyderHugues HoppeYonatan Wexler
    • Mark FinchJohn SnyderHugues HoppeYonatan Wexler
    • G06K9/46
    • G06T17/00G06T7/50
    • A dense guide image or signal is used to inform the reconstruction of a target image from a sparse set of target points. The guide image and the set of target points are assumed to be derived from a same real world subject or scene. Potential discontinuities (e.g., tears, edges, gaps, etc.) are first detected in the guide image. The potential discontinuities may be borders of Voronoi regions, perhaps computed using a distance in data space (e.g., color space). The discontinuities and sparse set of points are used to reconstruct the target image. Specifically, pixels of the target image may be interpolated smoothly between neighboring target points, but where neighboring target points are separated by a discontinuity, the interpolation may jump abruptly (e.g., by adjusting or influencing relaxation) at the discontinuity. The target points may be used to select only a subset of the discontinuities to be used during reconstruction.
    • 使用密集的引导图像或信号来通知来自稀疏目标点集合的目标图像的重建。 引导图像和目标点集合被假定为从相同的现实主题或场景导出。 在引导图像中首先检测到潜在的不连续性(例如,泪液,边缘,间隙等)。 潜在的不连续性可以是Voronoi区域的边界,可以使用数据空间中的距离(例如,颜色空间)来计算。 不连续点和稀疏集合点用于重建目标图像。 具体地说,目标图像的像素可以在相邻目标点之间平滑地内插,但是当相邻目标点被不连续性分开时,插值可能突然地跳跃(例如通过调节或影响松弛)而跳跃。 目标点可以用于仅在重建期间仅选择要使用的不连续的子集。
    • 7. 发明申请
    • Systems and methods for providing signal-specialized parametrization
    • 提供信号专门参数化的系统和方法
    • US20050225550A1
    • 2005-10-13
    • US11145196
    • 2005-06-03
    • Hugues HoppeJohn SnyderPedro SanderSteven Gortler
    • Hugues HoppeJohn SnyderPedro SanderSteven Gortler
    • G06T17/20G06T15/00G09G5/00
    • G06T17/205G06T17/20
    • Systems and methods are provided for optimizing a parametrization scheme in accordance with information about the surface signal. A surface parametrization is created to store a given surface signal into a texture image. The signal-specialized metric of the invention minimizes signal approximation error, i.e., the difference between the original surface signal and its reconstruction from the sampled texture. A signal-stretch parametrization metric is derived based on a Taylor expansion of signal error. For fast evaluation, the metric of the invention is pre-integrated over the surface as a metric tensor. The resulting parametrizations have increased texture resolution in surface regions with greater signal detail. Compared to traditional geometric parametrizations, the number of texture samples can often be reduced by a significant factor for a desired signal accuracy.
    • 提供的系统和方法用于根据关于表面信号的信息优化参数化方案。 创建表面参数以将给定的表面信号存储到纹理图像中。 本发明的信号专用度量使信号近似误差最小化,即原始表面信号与其从采样纹理的重构之间的差异。 基于信号误差的泰勒扩展导出信号拉伸参数度量。 为了快速评估,本发明的度量作为度量张量在表面上预先集成。 所产生的参数化在具有更大信号细节的表面区域中增加了纹理分辨率。 与传统的几何参数化相比,纹理样本的数量通常可以通过一个重要的因素来减少所需的信号精度。
    • 8. 发明申请
    • Multi-chart geometry images
    • 多图几何图像
    • US20070296719A1
    • 2007-12-27
    • US11895179
    • 2007-08-23
    • Pedro SanderZoe WoodSteven GortlerJohn SnyderHugues Hoppe
    • Pedro SanderZoe WoodSteven GortlerJohn SnyderHugues Hoppe
    • G06T15/10
    • G06T17/20
    • Techniques and tools for mesh processing are described. For example, a multi-chart geometry image represents arbitrary surfaces on object models. The multi-chart geometry image is created by resampling a surface onto a regular 2D grid, using a flexible atlas construction to map the surface piecewise onto charts of arbitrary shape. This added flexibility reduces parameterization distortion and thus provides greater geometric fidelity, particularly for shapes with long extremities, high genus, or disconnected components. As another example, zippering creates a watertight surface on reconstructed triangle meshes. The zippering unifies discrete paths of samples along chart boundaries to form the watertight mesh.
    • 描述了网格处理的技术和工具。 例如,多图几何图形表示对象模型上的任意曲面。 多图几何图像是通过将表面重新采样到普通2 D格网上创建的,使用灵活的地图集结构将表面分段映射到任意形状的图表上。 这种增加的灵活性降低了参数化失真,从而提供更大的几何保真度,特别是对于具有长末端,高类别或断开组件的形状。 作为另一个例子,拉链在重建的三角形网格上形成水密表面。 拉链将样本的离散路径与图表边界统一起来形成水密网格。
    • 9. 发明申请
    • Multi-chart geometry images
    • 多图几何图像
    • US20050151733A1
    • 2005-07-14
    • US10755206
    • 2004-01-09
    • Pedro SanderZoe WoodSteven GortlerJohn SnyderHugues Hoppe
    • Pedro SanderZoe WoodSteven GortlerJohn SnyderHugues Hoppe
    • G06T17/20
    • G06T17/20
    • Techniques and tools for mesh processing are described. For example, a multi-chart geometry image represents arbitrary surfaces on object models. The multi-chart geometry image is created by resampling a surface onto a regular 2D grid, using a flexible atlas construction to map the surface piecewise onto charts of arbitrary shape. This added flexibility reduces parameterization distortion and thus provides greater geometric fidelity, particularly for shapes with long extremities, high genus, or disconnected components. As another example, zippering creates a watertight surface on reconstructed triangle meshes. The zippering unifies discrete paths of samples along chart boundaries to form the watertight mesh.
    • 描述了网格处理的技术和工具。 例如,多图几何图形表示对象模型上的任意曲面。 多图几何图像是通过将表面重新采样到常规2D网格上,使用灵活的图谱结构将表面分段映射到任意形状的图表上创建的。 这种增加的灵活性降低了参数化失真,从而提供更大的几何保真度,特别是对于具有长末端,高类别或断开组件的形状。 作为另一个例子,拉链在重建的三角形网格上形成水密表面。 拉链将样本的离散路径与图表边界统一起来形成水密网格。
    • 10. 发明申请
    • Systems and methods for optimizing geometric stretch of a parametrization scheme
    • 用于优化参数化方案的几何拉伸的系统和方法
    • US20050088438A1
    • 2005-04-28
    • US10978098
    • 2004-10-29
    • Hugues HoppeJohn SnyderPedro SanderSteven Gortler
    • Hugues HoppeJohn SnyderPedro SanderSteven Gortler
    • G06T17/20G06T17/00
    • G06T17/20
    • Systems and methods are provided for optimizing the geometric stretch of a parametrization scheme. Given an arbitrary mesh, the systems and methods construct a progressive mesh (PM) such that all meshes in the PM sequence share a common texture parametrization. The systems and methods minimize geometric stretch, i.e., small texture distances mapped onto large surface distances, to balance sampling rates over all locations and directions on the surface. The systems and methods also minimize texture deviation, i.e., “slippage” error based on parametric correspondence, to obtain accurate textured mesh approximations. The technique(s) begin by partitioning the mesh into charts using planarity and compactness heuristics. Then, the technique(s) proceed by creating a stretch-minimizing parametrization within each chart, and by resizing the charts based on the resulting stretch. Then, the technique(s) simplify the mesh while respecting the chart boundaries. Next, the parametrization is re-optimized to reduce both stretch and deviation over the whole PM sequence. The charts may then be packed into a texture atlas for improved texture mapping in connection with a parametrization scheme.
    • 提供了用于优化参数化方案的几何拉伸的系统和方法。 给定任意网格,系统和方法构造渐进网格(PM),使得PM序列中的所有网格共享共同的纹理参数化。 系统和方法使几何拉伸最小化,即映射到大表面距离上的小纹理距离,以平衡表面上所有位置和方向上的采样率。 系统和方法还使纹理偏差最小化,即基于参数对应的“滑移”误差,以获得精确的纹理网格近似。 该技术首先将网格划分为使用平面性和紧凑性启发式的图表。 然后,通过在每个图表内创建拉伸最小化参数化,并且基于所得的拉伸来调整图表大小来继续进行该技术。 然后,技术简化网格,同时遵循图表边界。 接下来,参数化被重新优化以减少整个PM序列的拉伸和偏差。 然后可以将图表打包到纹理图集中,以改进与参数化方案相关的纹理映射。