公开(公告)号：US20050093877A1

公开(公告)日：2005-05-05

申请号：US10983193

申请日：2004-11-05

申请人： Lifeng Wang ,  Sing Kang ,  Richard Szeliski ,  Heung-Yeung Shum ,  Baining Guo

发明人： Lifeng Wang ,  Sing Kang ,  Richard Szeliski ,  Heung-Yeung Shum ,  Baining Guo

IPC分类号： G09G5/00

CPC分类号： G06T11/001

摘要： A system and process for reconstructing optimal texture maps from multiple views of a scene is described. In essence, this reconstruction is based on the optimal synthesis of textures from multiple sources. This is generally accomplished using basic image processing theory to derive the correct weights for blending the multiple views. Namely, the steps of reconstructing, warping, prefiltering, and resampling are followed in order to warp reference textures to a desired location, and to compute spatially-variant weights for optimal blending. These weights take into consideration the anisotropy in the texture projection and changes in sampling frequency due to foreshortening. The weights are combined and the computation of the optimal texture is treated as a restoration problem, which involves solving a linear system of equations. This approach can be incorporated in a variety of applications, such as texturing of 3D models, analysis by synthesis methods, super-resolution techniques, and view-dependent texture mapping.

摘要翻译： 描述用于从场景的多个视图重建最佳纹理图的系统和过程。 实质上，这种重建是基于来自多个源的纹理的最佳合成。 这通常使用基本图像处理理论来实现，以导出用于混合多个视图的正确权重。 即，遵循重构，翘曲，预过滤和重采样的步骤，以便将参考纹理扭曲到期望的位置，并计算用于最佳混合的空间变体权重。 这些权重考虑到纹理投影中的各向异性和由于缩短引起的采样频率的变化。 权重相结合，最优纹理的计算被视为恢复问题，其涉及求解线性方程组。 这种方法可以并入各种应用中，例如3D模型的纹理化，通过合成方法的分析，超分辨率技术和视图相关的纹理映射。

公开(公告)号：US20050285872A1

公开(公告)日：2005-12-29

申请号：US11192639

申请日：2005-07-28

申请人： Lifeng Wang ,  Sing Bing Kang ,  Richard Szeliski ,  Heung-Yeung Shum ,  Baining Guo

发明人： Lifeng Wang ,  Sing Bing Kang ,  Richard Szeliski ,  Heung-Yeung Shum ,  Baining Guo

IPC分类号： G06T15/20 ,  G09G5/00

CPC分类号： G06T15/04

摘要： A system and process for reconstructing optimal texture maps from multiple views of a scene is described. In essence, this reconstruction is based on the optimal synthesis of textures from multiple sources. This is generally accomplished using basic image processing theory to derive the correct weights for blending the multiple views. Namely, the steps of reconstructing, warping, prefiltering, and resampling are followed in order to warp reference textures to a desired location, and to compute spatially-variant weights for optimal blending. These weights take into consideration the anisotropy in the texture projection and changes in sampling frequency due to foreshortening. The weights are combined and the computation of the optimal texture is treated as a restoration problem, which involves solving a linear system of equations. This approach can be incorporated in a variety of applications, such as texturing of 3D models, analysis by synthesis methods, super-resolution techniques, and view-dependent texture mapping.

摘要翻译： 描述用于从场景的多个视图重建最佳纹理图的系统和过程。 实质上，这种重建是基于来自多个源的纹理的最佳合成。 这通常使用基本图像处理理论来实现，以导出用于混合多个视图的正确权重。 即，遵循重构，翘曲，预过滤和重采样的步骤，以便将参考纹理扭曲到期望的位置，并计算用于最佳混合的空间变体权重。 这些权重考虑到纹理投影中的各向异性和由于缩短引起的采样频率的变化。 权重相结合，最优纹理的计算被视为恢复问题，其涉及求解线性方程组。 这种方法可以并入各种应用中，例如3D模型的纹理化，通过合成方法的分析，超分辨率技术和视图相关的纹理映射。

公开(公告)号：US06985156B2

公开(公告)日：2006-01-10

申请号：US10875741

申请日：2004-06-23

申请人： Lifeng Wang ,  Sing Bing Kang ,  Richard Szeliski ,  Heung-Yeung Shum ,  Baining Guo

发明人： Lifeng Wang ,  Sing Bing Kang ,  Richard Szeliski ,  Heung-Yeung Shum ,  Baining Guo

IPC分类号： G09G5/00

CPC分类号： G06T11/001

摘要： A system and process for reconstructing optimal texture maps from multiple views of a scene is described. In essence, this reconstruction is based on the optimal synthesis of textures from multiple sources. This is generally accomplished using basic image processing theory to derive the correct weights for blending the multiple views. Namely, the steps of reconstructing, warping, prefiltering, and resampling are followed in order to warp reference textures to a desired location, and to compute spatially-variant weights for optimal blending. These weights take into consideration the anisotropy in the texture projection and changes in sampling frequency due to foreshortening. The weights are combined and the computation of the optimal texture is treated as a restoration problem, which involves solving a linear system of equations. This approach can be incorporated in a variety of applications, such as texturing of 3D models, analysis by synthesis methods, super-resolution techniques, and view-dependent texture mapping.

摘要翻译： 描述用于从场景的多个视图重建最佳纹理图的系统和过程。 实质上，这种重建是基于来自多个源的纹理的最佳合成。 这通常使用基本图像处理理论来实现，以导出用于混合多个视图的正确权重。 即，遵循重构，翘曲，预过滤和重采样的步骤，以便将参考纹理扭曲到期望的位置，并计算用于最佳混合的空间变体权重。 这些权重考虑到纹理投影中的各向异性和由于缩短引起的采样频率的变化。 权重相结合，最优纹理的计算被视为恢复问题，其涉及求解线性方程组。 这种方法可以并入各种应用中，例如3D模型的纹理化，通过合成方法的分析，超分辨率技术和视图相关的纹理映射。

公开(公告)号：US07205998B2

公开(公告)日：2007-04-17

申请号：US11192639

申请日：2005-07-28

申请人： Lifeng Wang ,  Sing Bing Kang ,  Richard Szeliski ,  Heung-Yeung Shum ,  Baining Guo

发明人： Lifeng Wang ,  Sing Bing Kang ,  Richard Szeliski ,  Heung-Yeung Shum ,  Baining Guo

IPC分类号： G09G5/00

CPC分类号： G06T15/04

摘要： A system and process for reconstructing optimal texture maps from multiple views of a scene is described. In essence, this reconstruction is based on the optimal synthesis of textures from multiple sources. This is generally accomplished using basic image processing theory to derive the correct weights for blending the multiple views. Namely, the steps of reconstructing, warping, prefiltering, and resampling are followed in order to warp reference textures to a desired location, and to compute spatially-variant weights for optimal blending. These weights take into consideration the anisotropy in the texture projection and changes in sampling frequency due to foreshortening. The weights are combined and the computation of the optimal texture is treated as a restoration problem, which involves solving a linear system of equations. This approach can be incorporated in a variety of applications, such as texturing of 3D models, analysis by synthesis methods, super-resolution techniques, and view-dependent texture mapping.

摘要翻译： 描述用于从场景的多个视图重建最佳纹理图的系统和过程。 实质上，这种重建是基于来自多个源的纹理的最佳合成。 这通常使用基本图像处理理论来实现，以导出用于混合多个视图的正确权重。 即，遵循重构，翘曲，预过滤和重采样的步骤，以便将参考纹理扭曲到期望的位置，并计算用于最佳混合的空间变体权重。 这些权重考虑到纹理投影中的各向异性和由于缩短引起的采样频率的变化。 权重相结合，最优纹理的计算被视为恢复问题，其涉及求解线性方程组。 这种方法可以并入各种应用中，例如3D模型的纹理化，通过合成方法的分析，超分辨率技术和视图相关的纹理映射。

公开(公告)号：US06999095B2

公开(公告)日：2006-02-14

申请号：US10983193

申请日：2004-11-05

申请人： Lifeng Wang ,  Sing Bing Kang ,  Richard Szeliski ,  Heung-Yeung Shum ,  Baining Guo

发明人： Lifeng Wang ,  Sing Bing Kang ,  Richard Szeliski ,  Heung-Yeung Shum ,  Baining Guo

IPC分类号： G09G5/00

CPC分类号： G06T11/001

摘要： A system and process for reconstructing optimal texture maps from multiple views of a scene is described. In essence, this reconstruction is based on the optimal synthesis of textures from multiple sources. This is generally accomplished using basic image processing theory to derive the correct weights for blending the multiple views. Namely, the steps of reconstructing, warping, prefiltering, and resampling are followed in order to warp reference textures to a desired location, and to compute spatially-variant weights for optimal blending. These weights take into consideration the anisotropy in the texture projection and changes in sampling frequency due to foreshortening. The weights are combined and the computation of the optimal texture is treated as a restoration problem, which involves solving a linear system of equations. This approach can be incorporated in a variety of applications, such as texturing of 3D models, analysis by synthesis methods, super-resolution techniques, and view-dependent texture mapping.

公开(公告)号：US06825850B2

公开(公告)日：2004-11-30

申请号：US10283562

申请日：2002-10-30

申请人： Lifeng Wang ,  Sing Bing Kang ,  Richard Szeliski ,  Heung-Yeung Shum ,  Baining Guo

发明人： Lifeng Wang ,  Sing Bing Kang ,  Richard Szeliski ,  Heung-Yeung Shum ,  Baining Guo

IPC分类号： G09G500

CPC分类号： G06T11/001

摘要： A system and process for reconstructing optimal texture maps from multiple views of a scene is described. In essence, this reconstruction is based on the optimal synthesis of textures from multiple sources. This is generally accomplished using basic image processing theory to derive the correct weights for blending the multiple views. Namely, the steps of reconstructing, warping, prefiltering, and resampling are followed in order to warp reference textures to a desired location, and to compute spatially-variant weights for optimal blending. These weights take into consideration the anisotropy in the texture projection and changes in sampling frequency due to foreshortening. The weights are combined and the computation of the optimal texture is treated as a restoration problem, which involves solving a linear system of equations. This approach can be incorporated in a variety of applications, such as texturing of 3D models, analysis by synthesis methods, super-resolution techniques, and view-dependent texture mapping.

公开(公告)号：US20050093857A1

公开(公告)日：2005-05-05

申请号：US10698909

申请日：2003-10-31

申请人： Lifeng Wang ,  Xi Wang ,  Xing Tong ,  Baining Guo ,  Heung-Yeung Shum

发明人： Lifeng Wang ,  Xi Wang ,  Xing Tong ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G06T15/20 ,  G06T15/00

CPC分类号： G06T15/04

摘要： A computer implemented method for generating a representation of structure for use in rendering a synthesized image is provided. The representation is a view-dependent displacement mapping that represents displacements along a viewing direction. This view dependency allows the representation to be used to determine self shadows as well as shading, occlusion and silhouettes when used during rendering for synthesis.

摘要翻译： 提供了一种用于生成用于渲染合成图像的结构的表示的计算机实现的方法。 该表示是视图相关的位移映射，其表示沿观察方向的位移。 该视图依赖性允许在用于合成的渲染期间使用表示来确定自身阴影以及阴影，遮挡和剪影。

公开(公告)号：US20070018996A1

公开(公告)日：2007-01-25

申请号：US11189491

申请日：2005-07-25

申请人： Lifeng Wang ,  Xu Yang ,  Baining Guo ,  Heung-Yeung Shum

发明人： Lifeng Wang ,  Xu Yang ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G09G5/02

CPC分类号： G06T15/50

摘要： Rendering of a partially translucent object is performed using a set of parameter maps derived from data measuring reflectance and transmittance of light received at the surface of the partially translucent object. Data is captured from an actual object being modeled, rather than estimated based on internal structure and composition. Parameter maps relating albedo, thickness variation, and specular intensity and roughness are stored as textures to facilitate rendering. In addition, realistic illumination from high energy sources such as sunlight is effected by separating light into low frequency and high frequency components. Low frequency components are rendered by precomputed radiance transfer. High frequency components, which are not modeled well by precomputed radiance transfer, are modeled using a light visibility convolution integral to generate light visibility maps for positions of the high frequency light source. Contributions from the different frequency components are combined to yield a realistic appearance.

摘要翻译： 使用从测量在部分半透明物体的表面处接收的光的反射率和透射率的数据导出的一组参数图来执行部分半透明物体的渲染。 数据从被建模的实际对象中获取，而不是基于内部结构和组合来估计。 将反照率，厚度变化和镜面强度和粗糙度相关的参数图存储为纹理以便于渲染。 此外，通过将光分离成低频和高频分量来实现来自诸如阳光的高能源的现实照明。 低频分量通过预先计算的辐射传输来渲染。 通过预先计算的辐射传输良好地建模的高频分量使用光可见度卷积积分来建模，以产生高频光源的位置的光可见度图。 来自不同频率分量的贡献被组合以产生现实的外观。

公开(公告)号：US07129943B2

公开(公告)日：2006-10-31

申请号：US10295570

申请日：2002-11-15

申请人： Zhunping Zhang ,  Lifeng Wang ,  Baining Guo ,  Heung-Yeung Shum

发明人： Zhunping Zhang ,  Lifeng Wang ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G06T15/00

CPC分类号： G06T15/205

摘要： A “light field morpher,” as described herein, provides a computationally efficient system and method for image-based three-dimensional (3D) morphing and texture transfer of 3D objects by morphing “light fields” or “lumigraphs,” associated with source and target 3D objects. The light field morpher is applicable to morphing of objects having either or both Lambertian, or non-Lambertian surfaces, including surfaces having complex properties such as fur, subsurface scattering, and hypertextures, without the need for object modeling, or otherwise recovering detailed object geometry. Light field morphing begins by first specifying corresponding 2D and 3D feature elements, such as, “feature lines,” “feature polygons,” and “background edges,” in the input light fields representing the source and target light fields. Once the feature elements have been specified, “ray-space warping” of both light fields then warps those light fields to produce feature alignment. These warped light fields are then blended to produce a light field morph.

摘要翻译： 如本文所述，“光场变形者”提供了一种用于基于图像的三维（3D）变形和3D对象的纹理传输的计算有效的系统和方法，通过变形与光源相关的“光场”或“光谱”， 目标3D对象。 光场morpher适用于具有Lambertian或非朗伯表面的物体的变形，包括具有复杂特性的表面，如毛皮，地下散射和超纹理，而不需要对象建模，或以其他方式恢复详细的物体几何 。 光场变形首先在表示源和目标光场的输入光场中首先指定相应的2D和3D特征元素，例如“特征线”，“特征多边形”和“背景边缘”。 一旦特征元素被指定，两个光场的“射线空间翘曲”就会扭曲这些光场以产生特征对准。 然后将这些弯曲的光场混合以产生光场变形。

公开(公告)号：US20060170695A1

公开(公告)日：2006-08-03

申请号：US11045868

申请日：2005-01-28

申请人： Kun Zhou ,  Baining Guo ,  Heung-Yeung Shum ,  Lifeng Wang ,  Yasuyuki Matsushita

发明人： Kun Zhou ,  Baining Guo ,  Heung-Yeung Shum ,  Lifeng Wang ,  Yasuyuki Matsushita

IPC分类号： G09G5/00

CPC分类号： G06T15/04 ,  G06T17/20

摘要： Surfaces can be decorated with texture tiling and/or texture painting using one or more sample textures, such as BTFs. In a described implementation of texture tiling, a patch-based BTF synthesis algorithm is utilized. In an example embodiment, a mesh of a target surface is re-sampled to produce a dense mesh such that there is a one-to-one correspondence between vertices of the dense mesh and pixels of an image. Patch matching is then employed with a working image that corresponds to a working patch. In an example embodiment, the patch matching is effectuated using translations and rotations of the sample texture. In a described implementation of texture painting, irregular feature(s) of a sample texture are synthesized onto a target surface. In an example embodiment, user-specified constraints as to a desired foreground feature of a sample texture and an intended foreground region of a targeted surface are factored into a graphcut operation.