Abstract: Scenes of objects, such as models in three-dimensional environments and user interface elements in window-based computing environments, are often rendered with shadows cast by a first object on a second object based on a light source. Full graphics engines often produce rich and high-fidelity shadows but involve extensive computation that may be unsuitable for some lower-powered devices. Simple shadowing techniques, such as drop shadows, may be rendered with modest computational processing, but only within significant restrictions and with poor fidelity. Presented herein is a shadow rendering technique that involves identifying a silhouette cast by an object due to a light source and applying a geometric transform, based upon the positions of the objects and the light source within the scene. The shadows may further include variations for opacity and/or edge blurring, reflecting distances between the light source and the objects, and colored shadows that exhibit translucency as a stained-glass effect.

Abstract: A scene may be rendered as objects that are lit by various light sources. A scene designer may arrange the scene to create particular lighting effects when viewed from an initial perspective, such as gloss, translucency, and iridescence, and may choose lighting effects to create a desired aesthetic tone and/or highlighting within the scene. However, rendering the scene from a different perspective may alter the lighting effects (e.g., losing or misplacing desired lighting effects, and/or creating new and undesirable lighting effects, such as glare). Instead, when the scene is rendered from the initial perspective, the lighting effects created therein may be stored with the scene representation of the scene. A second rendering of the scene from a different perspective may reapply the stored lighting effects to the lit objects, thereby maintaining the lighting effects and the intent of the designer in the presentation of the scene from a different perspective.

Abstract: A scene may be rendered as objects that are lit by various light sources. A scene designer may arrange the scene to create particular lighting effects when viewed from an initial perspective, such as gloss, translucency, and iridescence, and may choose lighting effects to create a desired aesthetic tone and/or highlighting within the scene. However, rendering the scene from a different perspective may alter the lighting effects (e.g., losing or misplacing desired lighting effects, and/or creating new and undesirable lighting effects, such as glare). Instead, when the scene is rendered from the initial perspective, the lighting effects created therein may be stored with the scene representation of the scene. A second rendering of the scene from a different perspective may reapply the stored lighting effects to the lit objects, thereby maintaining the lighting effects and the intent of the designer in the presentation of the scene from a different perspective.

Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.

Abstract: Described herein are technologies pertaining to generating a relatively accurate virtual three-dimensional model of a head/face of a user. Depth frames are received from a depth sensor and color frames are received from a camera, wherein such frames capture a head of a user. Based upon the depth frames and the color frames, the three-dimensional model of the head of the user is generated.

Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.

Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.

Abstract: Described herein are technologies pertaining to generating a relatively accurate virtual three-dimensional model of a head/face of a user. Depth frames are received from a depth sensor and color frames are received from a camera, wherein such frames capture a head of a user. Based upon the depth frames and the color frames, the three-dimensional model of the head of the user is generated.

Abstract: Techniques to sample texels efficiently for an image effect may include determining a number of texels (kernel size) needed to compute a weighted average for an image effect on an image. The technique may further include selecting at least one mipmap generated by a graphics processing unit (GPU) according to a function of the determined kernel size. The function may also consider a threshold kernel size. The technique may further sampling texels, with the GPU, from the selected mipmap(s), and calculate the weighted average of the sampled texels to produce the image effect.

Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.

Abstract: 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. An adaptive marching cubes procedure is performed on the GPU to extract an isosurface of the implicit function as a triangular mesh.

Abstract: Triangles are tessellated by an algorithm that is adapted for efficient parallel processing. A plurality of input triangles for tessellation are received. Within each input triangle, a number of tessellated vertices and a number of output triangles to be generated are calculated. A scan-based methodology accesses data stored in lookup tables to generate locations of the output triangles within the input triangle. In some implementations, multiple output triangles within the input triangle are generated simultaneously by parallel processing. A tessellated input triangle is divided into the multiple output triangles that are rendered in a computer graphic system.

Abstract: Techniques to sample texels efficiently for an image effects are discussed. A technique may include determining a number of texels (kernel size) needed to compute a weighted average for an image effect on an image. The technique may further include selecting at least one mipmap generated by a graphics processing unit (GPU) according to a function of the determined kernel size. The function may also consider a threshold kernel size. The technique may further sampling texels, with the GPU, from the selected mipmap(s), and calculate the weighted average of the sampled texels to produce the image effect. Other embodiments are described and claimed.

Abstract: 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.

Abstract: Disclosed is a system and method for determining, in parallel on a graphics processing unit, a block compression case which results in a least error to a block. Once determined, the block compression case may be used to compress the block.

Abstract: Triangles are tessellated by an algorithm that is adapted for efficient parallel processing. A plurality of input triangles for tessellation are received. Within each input triangle, a number of tessellated vertices and a number of output triangles to be generated are calculated. A scan-based methodology accesses data stored in lookup tables to generate locations of the output triangles within the input triangle. In some implementations, multiple output triangles within the input triangle are generated simultaneously by parallel processing. A tessellated input triangle is divided into the multiple output triangles that are rendered in a computer graphic system.

Abstract: A real-time algorithm for rendering of an inhomogeneous scattering medium such as fog with a surface object immersed therein is described. An input media animation is represented as a sequence of density fields. The algorithm computes surface reflectance of the surface object in the inhomogeneous scattering medium. The algorithm may also compute airlight of the inhomogeneous scattering medium. Several approximations are taken which lead to analytical solutions of quantities such as optical depth integrations and single scattering integrations, and a reduced number of integrations that need to be calculated. The resultant algorithm is able to render inhomogeneous media including their shadowing and scattering effects in real time. The algorithm may be adopted for a variety of light sources including point lights and environmental lights.

Abstract: A real-time algorithm for rendering an inhomogeneous scattering medium such as fog is described. An input media animation is represented as a sequence of density fields, each of which is decomposed into a weighted sum of a set of radial basis functions (RBFs) such as Gaussians. The algorithm computes airlight and surface reflectance of the inhomogeneous scattering medium. Several approximations are taken which lead to analytical solutions of quantities such as an optical depth integrations and single scattering integrations, and a reduced number of integrations that need to be calculated. The resultant algorithm is able to render inhomogeneous media including their shadowing and scattering effects in real time. The algorithm may be adopted for a variety of light sources including point lights and environmental lights.

Abstract: 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.

Abstract: 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.