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: 20110012910Abstract: A system is described for using a texture synthesis approach to produce digital images that simulate motion. The system operates by receiving a large-scale motion image that describes large-scale motion, as well as one or more exemplar images that describes small-scale motion. The system then applies a texture synthesis approach to duplicate the small-scale motion described in the exemplar image(s), as guided by the large-scale motion described in the large-scale motion image. This operation produces a synthesized motion image. The system then combines the synthesized motion image with the large-scale motion image to produce a combined motion image. The combined motion image presents the large-scale motion as modulated by the small-scale motion. The system can also take account for one or more application-specific constraints, such as incompressibility and boundary conditions.Type: ApplicationFiled: July 15, 2009Publication date: January 20, 2011Applicant: Microsoft CorporationInventors: Li-Yi Wei, Chongyang Ma, Baining Guo, Kun Zhou
-
Patent number: 7872653Abstract: This disclosure describes a variational framework for detail-preserving skinned mesh manipulation or deformation. The skinned mesh deformation occurs by optimizing skeleton position and vertex weights of a skeletal skinned mesh in an integrated manner. The process allows creating new poses and animations by specifying a few desired constraints for the skeletal skinned mesh in an interactive deformation platform. This process adjusts the skeletal position and solves for a deformed skinned mesh simultaneously with an algorithm in conjunction with the constraints. The algorithm includes a cascading optimization procedure. The mesh puppetry displays skinned mesh manipulation in real-time. The user interface will enable interactive design in creating new poses and animations for a skeletal skinned mesh, enabling direct manipulation of the skeletal skinned mesh to create natural, life-like poses, and providing automatic balancing and most-rigid constraints to create a puppet-like animation.Type: GrantFiled: June 18, 2007Date of Patent: January 18, 2011Assignee: Microsoft CorporationInventors: Kun Zhou, Xiaohan Shi, Baining Guo
-
Patent number: 7868885Abstract: A graphics system allows for manipulation of a detail mesh for a subdivision surface. To deform the subdivision surface, the graphics system generates a corresponding deformed control mesh by attempting to satisfy both position constraints of the manipulation and Laplacian constraints for the detail mesh. After the deformed control mesh is generated, the deformed detail mesh can be generated by applying a subdivision function to the deformed control mesh to generate a deformed smooth mesh and then applying detail information to the deformed smooth mesh.Type: GrantFiled: June 22, 2007Date of Patent: January 11, 2011Assignee: Microsoft CorporationInventors: Kun Zhou, Heung-Yeung Shum, Baining Guo, Xin Huang, Weiwei Xu
-
Patent number: 7843467Abstract: A method and system is provided for deforming a shape of an image. In one example, an input is received for deforming a displayed shape, the shape including a boundary polygon or outline contour and a local area within the outline contour. The local area may further include vertices and edges. During deformation, an energy function corresponding to the outline contour and the local area may be determined and reduced or minimized. Positioning of the vertices and lengths of the edges may be determined based on the energy function or preservation of coordinates associated with the outline contour and the local area.Type: GrantFiled: December 18, 2006Date of Patent: November 30, 2010Assignee: Microsoft CorporationInventors: Kun Zhou, Weiwei Xu, Baining Guo
-
Patent number: 7843456Abstract: Gradient domain editing of animated meshes is described. Exemplary systems edit deforming mesh sequences by applying Laplacian mesh editing techniques in the spacetime domain. A user selects relevant frames or handles to edit and the edits are propagated to the entire sequence. For example, if the mesh depicts an animated figure, then user-modifications to position of limbs, head, torso, etc., in one frame are propagated to the entire sequence. In advanced editing modes, a user can reposition footprints over new terrain and the system automatically conforms the walking figure to the new footprints. A user-sketched curve can automatically provide a new motion path. Movements of one animated figure can be transferred to a different figure. Caricature and cartoon special effects are available. The user can also select spacetime morphing to smoothly change the shape and motion of one animated figure into another over a short interval.Type: GrantFiled: June 29, 2007Date of Patent: November 30, 2010Assignee: Microsoft CorporationInventors: Weiwei Xu, Kun Zhou, Yizhou Yu, Baining Guo
-
Publication number: 20100277477Abstract: Described is a search technology in which spatially varying anisotropic reflectance is modeled using image data captured from a single view. Reflectance at each point is represented using a microfacet-based Bidirectional Reflectance Distribution Function (BRDF). Modeling processes the image data, which provides a partial normal distribution function (NDF) for each surface point. The NDF at each selected point is completed by texture synthesis using similar, overlapping partial NDFs from other points. Also described is a scanning device that illuminates a sample surface from a two-dimensional set of light directions using a linear array of LEDs moved over a flat sample.Type: ApplicationFiled: May 1, 2009Publication date: November 4, 2010Applicant: Microsoft CorporationInventors: Jiaping Wang, Shuang Zhao, Xin Tong, John M. Snyder, Baining Guo
-
Patent number: 7800627Abstract: Mesh quilting for geometric texture synthesis involves synthesizing a geometric texture by quilting a mesh texture swatch. In an example embodiment, geometry is matched between a mesh texture swatch and a portion of a synthesized geometric texture. Correspondences are ascertained between elements of the mesh texture swatch and the portion of the synthesized geometric texture. The ascertained corresponding elements of the mesh texture swatch and the portion of the synthesized geometric texture are aligned via local deformation to create a new patch. The new patch is merged into an output texture space to grow the synthesized geometric texture.Type: GrantFiled: June 8, 2007Date of Patent: September 21, 2010Assignee: Microsoft CorporationInventors: Kun Zhou, Xin Huang, Xi Wang, Baining Guo, Heung-Yeung Shum
-
Publication number: 20100085352Abstract: Described is a technology in which point cloud surface reconstruction is performed via parallel processing on a graphics processing unit, achieving real-time reconstruction rates. An octree is built for a given set of oriented points, with each node containing a set of points enclosed by the node. The data structure is built on the GPU, in parallel, using level-order traversals to process nodes at a same tree level. The surface is reconstructed based on data configured and located via the traversals. To produce the surface, an implicit function over the volume spanned by the octree nodes is computed using the GPU, e.g., based on a Poisson surface reconstruction method. A sparse linear system is built and a multi-grid solver is employed to solve the system.Type: ApplicationFiled: October 4, 2008Publication date: April 8, 2010Applicant: MICROSOFT CORPORATIONInventors: Kun Zhou, Xin Huang, Minmin Gong, Baining Guo
-
Publication number: 20100085360Abstract: Techniques are described for rendering a volume of scattering media, in particular by computing radiances of points or voxels in the scattering media. A set of sample points in the scattering media are found. Radiances of the sample points are computed. Radiance gradients of the sample points are computed from the radiances. The radiances and gradients are used to interpolate radiances throughout the scattering media. The set of sample points may be computed in an iterative dynamic manner in order to concentrate samples near features (e.g., shadow edges) of the scattering media.Type: ApplicationFiled: October 4, 2008Publication date: April 8, 2010Applicant: MICROSOFT CORPORATIONInventors: Zhong Ren, Kun Zhou, Stephen Lin, Baining Guo
-
Publication number: 20100085353Abstract: Described is a technology by which a user interacts with a surface representative of a point cloud data to correct for imperfect scan data. The surface is reconstructed based on the interaction. Real time viewing of the image is facilitated by parallel surface reconstruction. For example, the user may draw strokes to reduce topological ambiguities in poorly-sampled areas. An algorithm automatically adds new oriented sample points to the original point cloud based on the user interaction. Then a new isosurface is generated for the augmented point cloud. The user also may specify the geometry of missing areas of the surface. The user copies a set of points from another point cloud, and places the points around the target area. A new isosurface is then generated.Type: ApplicationFiled: October 4, 2008Publication date: April 8, 2010Applicant: MICROSOFT CORPORATIONInventors: Kun Zhou, Xin Huang, Baining Guo
-
Publication number: 20100082704Abstract: Described is a technology for constructing kd-trees on GPUs, in a manner that is sufficiently fast to achieve real-time performance by exploiting GPU-bsaed parallelism during the kd-tree construction. Tree nodes are built in breadth-first search order, e.g., to use a thread for each node at each level. For large nodes at upper tree levels, computations are parallelized over geometric primitives (instead of nodes). To this end, large nodes are split into child nodes by cutting off empty space based until an empty space ratio is achieved, and thereafter performing spatial splitting. Small nodes are split based on split candidate costs, e.g., computed by a surface area heuristic or a voxel volume heuristic (VVH).Type: ApplicationFiled: September 30, 2008Publication date: April 1, 2010Applicant: MICROSOFT CORPORATIONInventors: Kun Zhou, Hou Qiming, Baining Guo
-
Publication number: 20100079451Abstract: Described is a technology by which a ray tracer incorporates a GPU-based kd-tree builder for rendering arbitrary dynamic scenes. For each frame, the ray tracer builds a kd-tree for the scene geometry. The ray tracer spawns and traces eye rays, reflective and refractive rays, and shadow rays. For each ray to be traced, the ray tracer walks through the kd-tree until it reaches leaf nodes and associated triangles. When a ray passes through both sides of a splitting plane, the “far” sub-tree is pushed into the stack and the “near” sub-tree is traversed first.Type: ApplicationFiled: September 30, 2008Publication date: April 1, 2010Applicant: MICROSOFT CORPORATIONInventors: Kun Zhou, Hou Qiming, Baining Guo
-
Publication number: 20100082703Abstract: An octree GPU construction system and method for constructing a complete octree data structure on a graphics processing unit (GPU). Embodiments of the octree GPU construction system and method first defines a complete octree data structure as forming a complete partition of the 3-D space and including a vertex, edge, face, and node arrays, and neighborhood information. Embodiments of the octree GPU construction system and method input a point cloud and construct a node array. Next, neighboring nodes are computed for each of the nodes in the node arrays by using at least two pre-computed look-up tables (such as a parent look-up table and a child look-up table). Embodiments of the octree GPU construction system and method then use the neighboring nodes and neighborhood information to compute a vertex array, edge array, and face array are computed by determining owner information and self-ownership information based on the neighboring nodes.Type: ApplicationFiled: September 29, 2008Publication date: April 1, 2010Applicant: Microsoft CorporationInventors: Kun Zhou, Minmin Gong, Baining Guo
-
Publication number: 20100079452Abstract: Described is a technology by which a GPU-based photon mapping mechanism/algorithm uses a kd-tree to render arbitrary dynamic scenes. For each frame, the mechanism emits and traces a set of photons into the scene. When a photon hits a surface, it can either be reflected, transmitted, or absorbed based on the surface material. Once photon tracing is done, a kd-tree is built for the stored photons. To estimate the radiance value at an arbitrary surface point, the k-nearest photons are located and filtered. The photon tracing and photon kd-tree construction, as well as the radiance estimation using k-nearest neighbor (KNN) searches are performed on graphics hardware, e.g., a GPU. In one example, only caustic photons are traced, whereby a photon is terminated and stored once it hits a diffuse surface.Type: ApplicationFiled: September 30, 2008Publication date: April 1, 2010Applicant: MICROSOFT CORPORATIONInventors: Kun Zhou, Hou Qiming, Baining Guo
-
Patent number: 7663623Abstract: 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.Type: GrantFiled: December 18, 2006Date of Patent: February 16, 2010Assignee: Microsoft CorporationInventors: Kun Zhou, Jiaping Wang, Stephen Lin, Baining Guo
-
Publication number: 20100033482Abstract: Dynamic refractive object relighting technique embodiments are presented which involve rendering an image of a refractive object in a dynamic scene by first voxelizing a representation of the surfaces of the object into a volumetric representation in the form of a rectangular voxel grid. A refractive index is assigned to each voxel based on user-input material parameters. Next, the paths of photons are traced in a step-wise manner as each photon refracts through the object. The size of each step forward is variable and based on variations in refractive index of the object. Radiance values are assigned to all the voxels that the photons traverse in their paths through the object. An output image of the refractive object is then rendered from a user-input viewpoint by tracing viewing rays from the viewpoint into the scene and calculating the amount of radiance that reaches the viewpoint along each of the rays.Type: ApplicationFiled: August 11, 2008Publication date: February 11, 2010Applicant: Interactive Relighting of Dynamic Refractive ObjectsInventors: Kun Zhou, Xin Sun, Eric Stollnitz, Baining Guo
-
Publication number: 20100033488Abstract: An approach to enrich skeleton-driven animations with physically-based secondary deformation in real time is described. To achieve this goal, the technique described employs a surface-based deformable model that can interactively emulate the dynamics of both low- and high-frequency volumetric effects. Given a surface mesh and a few sample sequences of its physical behavior, a set of motion parameters of the material are learned during an off-line preprocessing step. The deformable model is then applicable to any given skeleton-driven animation of the surface mesh. Additionally, the described dynamic skinning technique can be entirely implemented on GPUs and executed with great efficiency. Thus, with minimal changes to the conventional graphics pipeline, the technique can drastically enhance the visual experience of skeleton-driven animations by adding secondary deformation in real time.Type: ApplicationFiled: August 11, 2008Publication date: February 11, 2010Applicant: MICROSOFT CORPORATIONInventors: Kun Zhou, Xiaohan Shi, Baining Guo
-
Publication number: 20090322769Abstract: Described is a technology in a computing environment comprising a programming language for general purpose computation on a graphics processing unit (GPU), along with an associated compiler. A Bulk-Synchronous GPU Programming (BSGP) program is programmed to include barriers to describe parallel processing on GPUs. A BSGP compiler detects barriers corresponding to supersteps, converts BSGP programs to kernels based on the barriers, and combines them. During compilation, the compiler aligns barriers in the statements and bundles the corresponding supersteps together. A par construct is provided to allow the programmer to control aspects of bundling, e.g., by specifying a block independent statements. Thread manipulation emulation is provided to transparently emulate thread creation and destruction, with operations fork and kill. Also provided is remote variable access intrinsics for efficient communications between threads, and collective primitive operations.Type: ApplicationFiled: June 26, 2008Publication date: December 31, 2009Applicant: MICROSOFT CORPORATIONInventors: Kun Zhou, Hou Qiming, Baining Guo
-
Patent number: 7610556Abstract: A dialog manager module accesses a dialog model, a discourse model and a domain model to render information to a computer user through the course of a dialog exchange with the computer user. Actions are performed according to a set of rules during the dialog. Each of the rules comprise an action to perform as a function of the current dialog state and a filled form of slots of semantic information of the user input.Type: GrantFiled: March 14, 2002Date of Patent: October 27, 2009Assignee: Microsoft CorporationInventors: Baining Guo, Bo Zhang, Heung-Yeung Shum
-
Patent number: 7609264Abstract: 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.Type: GrantFiled: March 29, 2006Date of Patent: October 27, 2009Assignee: Microsoft CorporationInventors: Xin Tong, Yanyun Chen, Baining Guo, Heung-Yeung Shum, Stephen Lin, Ying Song