-
公开(公告)号：US08948538B2
公开(公告)日：2015-02-03
申请号：US13556080
申请日：2012-07-23
Applicant: Stephen Lin , Baining Guo , Changyin Zhou
Inventor： Stephen Lin , Baining Guo , Changyin Zhou
CPC classification number: G06T5/005 , G06T2207/10004 , G06T2207/20021 , G06T2207/20182 , H04N1/409 , H04N5/2171 , H04N5/2178
Abstract: Removal of the effects of dust or other impurities on image data is described. In one example, a model of artifact formation from sensor dust is determined. From the model of artifact formation, contextual information in the image and a color consistency constraint may be applied on the dust to remove the dust artifacts. Artifacts may also be removed from multiple images from the same or different cameras or camera settings.
Abstract translation: 描述了去除灰尘或其他杂质对图像数据的影响。 在一个示例中，确定来自传感器灰尘的人造物形成的模型。 从人造物形成的模型，图像中的上下文信息和颜色一致性约束可以应用于灰尘以去除灰尘伪像。 人造物也可以从相同或不同的相机或相机设置的多个图像中移除。
-
公开(公告)号：US20120288196A1
公开(公告)日：2012-11-15
申请号：US13556080
申请日：2012-07-23
Applicant: Stephen Lin , Baining Guo , Changyin Zhou
Inventor： Stephen Lin , Baining Guo , Changyin Zhou
IPC: G06T5/00
CPC classification number: G06T5/005 , G06T2207/10004 , G06T2207/20021 , G06T2207/20182 , H04N1/409 , H04N5/2171 , H04N5/2178
Abstract: Removal of the effects of dust or other impurities on image data is described. In one example, a model of artifact formation from sensor dust is determined. From the model of artifact formation, contextual information in the image and a color consistency constraint may be applied on the dust to remove the dust artifacts. Artifacts may also be removed from multiple images from the same or different cameras or camera settings.
Abstract translation: 描述了去除灰尘或其他杂质对图像数据的影响。 在一个示例中，确定来自传感器灰尘的人造物形成的模型。 从人造物形成的模型，图像中的上下文信息和颜色一致性约束可以应用于灰尘以去除灰尘伪像。 人造物也可以从相同或不同的相机或相机设置的多个图像中移除。
-
公开(公告)号：US07548661B2
公开(公告)日：2009-06-16
申请号：US11384063
申请日：2006-03-17
Applicant: Stephen Lin , Baining Guo , Sing Bing Kang , Yuanjie Zheng
Inventor： Stephen Lin , Baining Guo , Sing Bing Kang , Yuanjie Zheng
IPC: G06K9/40
CPC classification number: H04N5/3572 , G06T5/007 , G06T7/11 , G06T2207/10024 , G06T2207/20012 , G06T2207/20016
Abstract: A system and process for determining the vignetting function of an image and using the function to correct for the vignetting is presented. The image can be any arbitrary image and no other images are required. The system and process is designed to handle both textured and untextured segments in order to maximize the use of available information. To extract vignetting information from an image, segmentation techniques are employed that locate image segments with reliable data for vignetting estimation. Within each image segment, the system and process capitalizes on frequency characteristics and physical properties of vignetting to distinguish it from other sources of intensity variation. The vignetting data acquired from segments are weighted according to a presented reliability measure to promote robustness in estimation.
Abstract translation: 提出了一种用于确定图像的渐晕功能并使用功能来校正渐晕的系统和过程。 图像可以是任意图像，并且不需要其他图像。 系统和过程被设计为处理纹理和非纹理段，以便最大限度地利用可用信息。 为了从图像中提取渐晕信息，采用定位图像片段以进行晕影估计的可靠数据的分割技术。 在每个图像片段中，系统和过程利用渐晕的频率特性和物理特性来区分其他强度变化的来源。 根据提出的可靠性度量对从片段获取的渐晕数据进行加权，以提高估计的鲁棒性。
-
公开(公告)号：US20080304764A1
公开(公告)日：2008-12-11
申请号：US11928951
申请日：2007-10-30
Applicant: Stephen Lin , Baining Guo , Changyin Zhou
Inventor： Stephen Lin , Baining Guo , Changyin Zhou
IPC: G06K9/40
CPC classification number: G06T5/005 , G06T2207/10004 , G06T2207/20021 , G06T2207/20182 , H04N1/409 , H04N5/2171 , H04N5/2178
Abstract: Removal of the effects of dust or other impurities on image data is described. In one example, a model of artifact formation from sensor dust is determined. From the model of artifact formation, contextual information in the image and a color consistency constraint may be applied on the dust to remove the dust artifacts. Artifacts may also be removed from multiple images from the same or different cameras or camera settings.
Abstract translation: 描述了去除灰尘或其他杂质对图像数据的影响。 在一个示例中，确定来自传感器灰尘的人造物形成的模型。 从人造物形成的模型，图像中的上下文信息和颜色一致性约束可以应用于灰尘以去除灰尘伪像。 人造物也可以从相同或不同的相机或相机设置的多个图像中移除。
-
公开(公告)号：US20080143719A1
公开(公告)日：2008-06-19
申请号：US11612394
申请日：2006-12-18
Applicant: Kun Zhou , Jiaping Wang , Stephen Lin , Baining Guo
Inventor： Kun Zhou , Jiaping Wang , Stephen Lin , Baining Guo
IPC: G06T15/50
CPC classification number: G06T15/55
Abstract: A method, device and system is provided for providing global illumination of a scene. For example, global illumination may be provided in a rendered 3-dimensional image that may contain objects and/or light sources. Radiance functions or visibility functions may further be represented by scaling of spherical harmonics functions in the spherical harmonics domain. For example, scaling of spherical harmonics coefficients corresponding to a spherical function may be performed based on a spherical harmonics scaling transformation matrix based on an angular scaling function.
Abstract translation: 提供了一种用于提供场景的全局照明的方法，装置和系统。 例如，可以在可以包含对象和/或光源的渲染的三维图像中提供全局照明。 亮度函数或可见度函数可以进一步通过球面谐波域中的球谐函数的缩放来表示。 例如，可以基于基于角度缩放函数的球面谐波缩放变换矩阵来执行对应于球面函数的球谐函数的缩放。
-
Patent Agency Ranking
公开(公告)号：US20070229502A1
公开(公告)日：2007-10-04
申请号：US11277935
申请日：2006-03-29
Applicant: Xin Tong , Yanyun Chen , Baining Guo , Heung-Yeung Shum , Stephen Lin , Ying Song
Inventor： Xin Tong , Yanyun Chen , Baining Guo , Heung-Yeung Shum , Stephen Lin , Ying Song
IPC: G06T15/50
CPC classification number: G06T15/55
Abstract: A shell radiance texture function (SRTF) is defined to record an outgoing radiance from a base volume of an object to be rendered. Using the SRTF, radiance values are precomputed and stored for the base volume. The object is rendered using the precomputed radiance values.
Abstract translation: 外壳辐射纹理函数（SRTF）被定义为记录要渲染的对象的基本卷的传出辐射。 使用SRTF，辐射值被预先计算并存储为基本卷。 使用预先计算的辐射值渲染对象。
-
公开(公告)号：US20070216680A1
公开(公告)日：2007-09-20
申请号：US11276931
申请日：2006-03-17
Applicant: Xi Wang , Xin Tong , Stephen Lin , Baining Guo
Inventor： Xi Wang , Xin Tong , Stephen Lin , Baining Guo
IPC: G06T17/00
CPC classification number: G06T15/04
Abstract: The present surface detail rendering technique provides an efficient technique for applying a mesostructure to a macrostructure for an object that minimizes the amount of memory required for pre-computed data. A leap texture is pre-computed for a mesostructure by classifying each voxel in the mesostructure geometry and assigning a value in the leap texture based upon the classification. The value in the leap texture represents a distance to jump along a ray cast in any view direction when a model is decorated with the mesostructure geometry.
Abstract translation: 目前的表面细节渲染技术提供了一种将介观结构应用于最小化预先计算数据所需的存储量的对象的宏结构的有效技术。 通过对介观结构几何中的每个体素进行分类，并根据分类在跳跃纹理中分配一个值，为中孔结构预先计算飞跃纹理。 跳跃纹理中的值表示当模型用介观结构几何形状装饰时沿着任何视图方向投射的光线跳跃的距离。
-
公开(公告)号：US07184052B2
公开(公告)日：2007-02-27
申请号：US10965603
申请日：2004-10-13
Applicant: Xi Wang , Xin Tong , Stephen Lin , Baining Guo , Heung-Yeung Shum
Inventor： Xi Wang , Xin Tong , Stephen Lin , Baining Guo , Heung-Yeung Shum
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：US20060279570A1
公开(公告)日：2006-12-14
申请号：US11147921
申请日：2005-06-08
Applicant: Kun Zhou , Yaohua Hu , Stephen Lin , Baining Guo , Heung-Yeung Shum
Inventor： Kun Zhou , Yaohua Hu , Stephen Lin , Baining Guo , Heung-Yeung Shum
IPC: G06T15/50
CPC classification number: G06T15/60
Abstract: Pre-computed shadow fields are described. In one aspect, shadow fields for multiple entities are pre-computed. The shadow fields are pre-computed independent of scene configuration. The multiple entities include at least one occluding object and at least one light source. A pre-computed shadow field for a light source indicates radiance from the light source. A pre-computed shadow field for an occluding object indicates occlusion of radiance from the at least one light source.
-
公开(公告)号：US20060204060A1
公开(公告)日：2006-09-14
申请号：US11435122
申请日：2006-05-16
Applicant: Ying Huang , Stephen Lin , Baining Guo , Heung-Yeung Shum
Inventor： Ying Huang , Stephen Lin , Baining Guo , Heung-Yeung Shum
IPC: G06K9/00
CPC classification number: G06K9/00335 , G10L2021/105
Abstract: A novel method for synchronizing the lips of a sketched face to an input voice. The lip synchronization system and method approach is to use training video as much as possible when the input voice is similar to the training voice sequences. Initially, face sequences are clustered from video segments, then by making use of sub-sequence Hidden Markov Models, a correlation between speech signals and face shape sequences is built. From this re-use of video, the discontinuity between two consecutive output faces is decreased and accurate and realistic synthesized animations are obtained. The lip synchronization system and method can synthesize faces from input audio in real-time without noticeable delay. Since acoustic feature data calculated from audio is directly used to drive the system without considering its phonemic representation, the method can adapt to any kind of voice, language or sound.
-
-
-
-
-
-
-
-
-
Search Results
30
records
(took 0.02 seconds)
