Patents by Inventor Baining Guo
Baining Guo has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20050115285Abstract: Knitwear modeling is disclosed. A macrostructure correponding to a three-dimensional object is generated, based on a stitch pattern and optionally a color pattern. Yarn microstructure is generated and applied to the macrostructure to yield a knitwear model. The stitch positions of the macrostructure can be perturbed to achieve stitch position irregularities. The fluffiness of the yarn microstructure can be controlled. In an alternative embodiment, a two-dimensional knitwear texture is generated, which can then be mapped to a three-dimensional object to yield a knitwear model.Type: ApplicationFiled: November 20, 2004Publication date: June 2, 2005Applicant: Microsoft CorporationInventors: Ying-Qing Xu, Baining Guo, Hua Zhong, Heung-Yeung Shum
-
Publication number: 20050099421Abstract: A method and system for efficient synthesis of photorealistic free-form knitwear, where a single cross-section of yarn serves as the basic primitive for modeling entire articles of knitwear. This primitive, called the lumislice, describes radiance from a yarn cross-section based on fine-level interactions, including occlusion, shadowing, and multiple scattering, among yarn fibers. By representing yarn as a sequence of identical but rotated cross-sections, the lumislice can effectively propagate local microstructure over arbitrary stitch patterns and knitwear shapes. This framework accommodates varying levels of detail and capitalizes on hardware-assisted transparency blending. To further enhance realism, a technique for generating soft shadows from yarn is also introduced.Type: ApplicationFiled: December 1, 2004Publication date: May 12, 2005Applicant: Microsoft CorporationInventors: Baining Guo, Steve Lin, Heung-Yeung Shum, Ying-Qing Xu, Yanyun Chen
-
Publication number: 20050093875Abstract: Methods for synthesizing progressively-variant textures based on texton masks are provided. A first method creates a synthesized texture image guided by a sample texture, first texton mask corresponding to the sample texture and a second texton mask modified based on the first texton mask. A second method also creates a synthesized texture image guided by a first and second sample textures and corresponding first and second texton masks. A method for rendering a synthesized texture on an image of a three-dimensional object includes creating a synthesized texture on the object guided by a two-dimensional progressively-variant sample texture, a texton mask for the sample texture and a mesh of a plurality of vertices representing the object.Type: ApplicationFiled: October 31, 2003Publication date: May 5, 2005Applicant: Microsoft CorporationInventors: Jingdan Zhang, Kun Zhou, Baining Guo, Heung-Yeung Shum
-
Publication number: 20050093877Abstract: 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.Type: ApplicationFiled: November 5, 2004Publication date: May 5, 2005Applicant: Microsoft CorporationInventors: Lifeng Wang, Sing Kang, Richard Szeliski, Heung-Yeung Shum, Baining Guo
-
Publication number: 20050093857Abstract: 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.Type: ApplicationFiled: October 31, 2003Publication date: May 5, 2005Applicant: Microsoft CorporationInventors: Lifeng Wang, Xi Wang, Xing Tong, Baining Guo, Heung-Yeung Shum
-
Publication number: 20050091616Abstract: A software-implemented transform and lighting module and pipeline designed and optimized for embedded platforms (such as mobile computing devices). The transform and lighting module and pipeline includes a number of features that make it well-suited for use on embedded devices. These features include a single streamline branched architecture that allows efficient processing on a CPU of an embedded device and saves computational time. This architecture is facilitated by use of a vertex cache that stores vertices as needed to avoid duplication in processing of the vertices. A culling feature culls vertices before lighting instead of lighting all vertices. A back face culling technique examines each of the vertices to determines whether a back face of a triangle is formed. If so, then the vertex is culled. A second technique involved determining whether a vertex is outside of one view frustum clip plane. If so, then the vertex is culled.Type: ApplicationFiled: September 18, 2003Publication date: April 28, 2005Applicant: Microsoft CorporationInventors: Lifeng Wang, Ke Deng, Baining Guo, Joshua Buckman
-
Publication number: 20050078124Abstract: A method and system uses geometry-driven feature point analysis to synthesize images including for example facial expressions. Given the feature point positions (geometry) of an expression, the method automatically synthesizes the corresponding expression image, which has photorealistic and natural looking expression details.Type: ApplicationFiled: October 14, 2003Publication date: April 14, 2005Applicant: Microsoft CorporationInventors: Zicheng Liu, Baining Guo, Heung-Yeung Shum, Qingshan Zhang
-
Publication number: 20050062762Abstract: A software-implemented graphics rendering system and method designed and optimized for embedded devices (such as mobile computing devices) using fixed-point operations including a variable-length fixed point representation for numbers and a normalized homogenous coordinates system for vector operations. The graphics rendering system and method includes a fixed-point mathematics library and graphics functions that includes optimized basic functions such as addition, subtraction, multiplication, division, all vertex operations, matrix operations, transform functions and lighting functions, and graphics functions. The mathematical library and graphics functions are modified and optimized by using a variable-length fixed-point representation and a normalized homogenous coordinate system (NHCS) for vector operations.Type: ApplicationFiled: September 13, 2003Publication date: March 24, 2005Applicant: Microsoft CorporationInventors: Lifeng Wang, Ke Deng, Baining Guo, Joshua Buckman
-
Patent number: 6871166Abstract: Knitwear modeling is disclosed. A macrostructure corresponding to a three-dimensional object is generated, based on a stitch pattern and optionally a color pattern. Yarn microstructure is generated and applied to the macrostructure to yield a knitwear model. The stitch positions of the macrostructure can be perturbed to achieve stitch position irregularities. The fluffiness of the yarn microstructure can be controlled. In an alternative embodiment, a two-dimensional knitwear texture is generated, which can then be mapped to a three-dimensional object to yield a knitwear model.Type: GrantFiled: July 23, 2000Date of Patent: March 22, 2005Assignee: Microsoft Corp.Inventors: Ying-Qing Xu, Baining Guo, Hua Zhong, Heung-Yeung Shum
-
Publication number: 20050012746Abstract: The present invention provides a systematic method for rendering feathers. In one aspect, a segment of a rachis having a first barb and second barb is generated. The first barb is generated based on a first barb length and the second barb is generated based on a second barb length.Type: ApplicationFiled: July 18, 2003Publication date: January 20, 2005Applicant: Microsoft CorporationInventors: Yanyun Chen, Baining Guo, Ying-Qing Xu, Heung-Yeung Shum
-
Publication number: 20050012741Abstract: The present invention provides a computer implemented method for placing feathers on a surface. The method includes providing a surface having a plurality of vertices and establishing a growing direction for each of the plurality of vertices on the surface. Feathers are placed on the surface based on the plurality of vertices and the growing direction.Type: ApplicationFiled: July 18, 2003Publication date: January 20, 2005Applicant: Microsoft CorporationInventors: Yanyun Chen, Baining Guo, Ying-Qing Xu, Heung-Yeung Shum
-
Patent number: 6825850Abstract: 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.Type: GrantFiled: October 30, 2002Date of Patent: November 30, 2004Assignee: Microsoft CorporationInventors: Lifeng Wang, Sing Bing Kang, Richard Szeliski, Heung-Yeung Shum, Baining Guo
-
Publication number: 20040233211Abstract: 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.Type: ApplicationFiled: June 23, 2004Publication date: November 25, 2004Applicant: Microsoft CorporationInventors: Lifeng Wang, Sing Bing Kang, Richard Szeliski, Heung-Yeung Shum, Baining Guo
-
Publication number: 20040222989Abstract: 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.Type: ApplicationFiled: November 15, 2002Publication date: November 11, 2004Inventors: Zhunping Zhang, Lifeng Wang, Baining Guo, Heung-Yeung Shum
-
Publication number: 20040215431Abstract: Knitwear modeling is disclosed. A macrostructure corresponding to a three-dimensional object is generated, based on a stitch pattern and optionally a color pattern. Yarn microstructure is generated and applied to the macrostructure to yield a knitwear model. The stitch positions of the macrostructure can be perturbed to achieve stitch position irregularities. The fluffiness of the yarn microstructure can be controlled. In an alternative embodiment, a two-dimensional knitwear texture is generated, which can then be mapped to a three-dimensional object to yield a knitwear model.Type: ApplicationFiled: May 21, 2004Publication date: October 28, 2004Applicant: Microsoft CorporationInventors: Ying-Qing Xu, Baining Guo, Hua Zhong, Heung-Yeung Shum
-
Publication number: 20040181382Abstract: Visualizing the surface of a liquid in real-time may be enabled using (i) a view-dependent representation of wave geometry and/or (ii) a Fresnel bump mapping for representing Fresnel reflection and refraction effects. In a described implementation, the liquid comprises an ocean that is simulated and rendered. In a first exemplary media implementation, electronically-executable instructions thereof direct an electronic device to execute operations that include: simulate a near patch of a surface of a liquid that is proximate to a viewpoint, the near patch including a representation of liquid waves in three dimensions; and simulate a far patch of the surface of the liquid that is distant from the viewpoint. In a second exemplary media implementation, instructions thereof direct actions that include: simulating a surface of a liquid to determine dimensional wave features; and rendering the surface of the liquid by applying a Fresnel texture map to the dimensional wave features.Type: ApplicationFiled: March 14, 2003Publication date: September 16, 2004Inventors: Yaohua Hu, Xin Tong, Baining Guo
-
Patent number: 6782130Abstract: A method, apparatus, and system are provided for rendering of photorealistic computer graphics images. According to one embodiment, an image is partitioned into regions, each of the regions having a discontinuity edge, a boundary, edge pixels along the boundary, and remaining pixels, and orientation of the discontinuity edge is estimated by computing a direction of least discrepancy within each of the regions by evaluating the edge pixels along the boundary of each of the regions.Type: GrantFiled: April 10, 2003Date of Patent: August 24, 2004Assignee: Intel CorporationInventor: Baining Guo
-
Patent number: 6765574Abstract: A method of scene simplification includes concurrently simplifying a plurality of objects in a scene represented by a hierarchical scene graph. The objects are represented as polygonal meshes and the hierachical scene graph includes a plurality of nodes, each node storing a mesh. The scene is a three dimensional scene and the objects are representations of three dimensional objects. Concurrently simplifying the plurality of objects includes determining an initial least level of detail polygon reduction ratio (LPPR) for at least one mesh, generating levels of detail variables for at least one mesh using the LPRR, and generating a simplified version of at least one mesh by using the levels of detail variables. The total number of polygons in a rendered scene may be set to correspond to a predetermined polygon budget.Type: GrantFiled: March 18, 2002Date of Patent: July 20, 2004Assignee: Intel CorporationInventors: Xiaodong Mao, Baining Guo
-
Patent number: 6762769Abstract: The present invention involves a new system and method for synthesizing textures from an input sample. A system and method according to the present invention uses a unique accelerated patch-based sampling system to synthesize high-quality textures in real-time using a small input texture sample. The patch-based sampling system of the present invention works well for a wide variety of textures ranging from regular to stochastic. Potential feature mismatches across patch boundaries are avoided by sampling patches according to a non-parametric estimation of the local conditional Markov Random Field (MRF) density function.Type: GrantFiled: January 23, 2002Date of Patent: July 13, 2004Assignee: Microsoft CorporationInventors: Baining Guo, Lin Liang, Heung-Yeung Shum, Ying-Qing Xu
-
Publication number: 20040120554Abstract: 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.Type: ApplicationFiled: December 21, 2002Publication date: June 24, 2004Inventors: Stephen Ssu-te Lin, Baining Guo, Heung-Yeung Shum