Abstract: A system generates a clothing deformation model which models one or more of a pose-dependent clothing shape variation which is induced by underlying body pose parameters, a pose-independent clothing shape variation which is induced by clothing size and underlying body shape parameters and a clothing shape variation including a combination of the pose-dependent clothing shape variation and/or the pose-independent clothing shape variation. The system generates, for an input human body, a custom-shaped garment associated with a clothing type by mapping, via the clothing deformation model, body shape parameters of the input human body to clothing shape parameters of the clothing type and dresses the input human body with the custom-shaped garment.

Abstract: Systems and methods for replacing a 2D image with an equivalent 3D image within a web page. The 2D image displayed within a web page may be identified and a 3D image with substantially equivalent content may also be identified. The 3D image may be integrated into the web page as a replacement to the 2D image. Further, at least one user input manipulating the 3D image within the web page may be received. The at least one user input may include movement of a view point (or point of view) of a user relative to a display displaying the web page and/or detection of a beam projected from an end of a user input device (and/or an end of the user input device) intersecting with the 3D image.

Abstract: Systems and methods for replacing a 2D image with an equivalent 3D image within a web page. Content of a 2D image displayed within a web page may be identified and 3D images may be identified as possible replacements of the 2D image. The 3D images may be ranked based on sets of ranking criteria. A 3D image with a highest-ranking value may be selected based on a ranking of the 3D images. The selected 3D image may be integrated into the web page, thereby replacing the 2D image with the selected 3D image. Further, a user input manipulating the 3D image within the web page may be received. The user input may include movement of a view point of a user relative to a display displaying the web page and/or detection of a beam projected from an end of a user input device intersecting with the 3D image.

Abstract: An image processing apparatus includes an image acquisition unit configured to acquire volume data, a feature point acquisition unit configured to acquire a coordinate of a feature point of an object in the volume data, a range setting unit configured to set a projection range defining a range of the volume data from which a projection image is to be generated, set a display range defining a range within which feature points are to be displayed, and adjust at least one of the projection range and the display range such that the projection range and the display range satisfy a predetermined relationship; and a display control unit configured to generate the projection image from the volume data according to the projection range and superimpose the feature point in the display range on the projection image.

Abstract: Ray tracing units, processing modules and methods are described for generating one or more reduced acceleration structures to be used for intersection testing in a ray tracing system for processing a 3D scene. Nodes of the reduced acceleration structure(s) are determined, wherein a reduced acceleration structure represents a subset of the 3D scene. The reduced acceleration structure(s) are stored for use in intersection testing. Since the reduced acceleration structures represent a subset of the scene (rather than the whole scene) the memory usage for storing the acceleration structure is reduced, and the latency in the traversal of the acceleration structure is reduced.

Abstract: This present disclosure relates to systems and processes for interpolating images of an object from a multi-directional structured image array. In particular embodiments, a plurality of images corresponding to a light field is obtained using a camera. Each image contains at least a portion of overlapping subject matter with another image. First, second, and third images are determined, which are the closest three images in the plurality of images to a desired image location in the light field. A first set of candidate transformations is identified between the first and second images, and a second set of candidate transformations is identified between the first and third images. For each pixel location in the desired image location, first and second best pixel values are calculated using the first and second set of candidate transformations, respectively, and the first and second best pixel values are blended to form an interpolated pixel.

Abstract: To use SIMD lanes efficiently for domain shader execution, domain point data from different domain shader patches may be packed together into a single SIMD thread. To generate an efficient code sequence, each domain point occupies one SIMD lane and all attributes for the domain point reside in their own partition of General Register File (GRF) space. This technique is called the multiple-patch SIMD dispatch mode.

Abstract: Techniques are disclosed for generating quality renderings of volumes by sampling a volume light by generating and analyzing a sparse voxel octree. In one embodiment, a volumetric light source may be divided into voxels and importance information stored in an octree. An importance value may be determined for each voxel based on the amount of emitted light in the region associated with that voxel. Importance values regarding the individual voxels may be stored in the leaves of the octree. Each interior node may be associated with an importance value equal to the sum of the importance values of its children. The root node may be associated with the total importance of the entire octree.

Abstract: A system generates a clothing deformation model which models one or more of a pose-dependent clothing shape variation which is induced by underlying body pose parameters, a pose-independent clothing shape variation which is induced by clothing size and underlying body shape parameters and a clothing shape variation including a combination of the pose-dependent clothing shape variation and/or the pose-independent clothing shape variation. The system generates, for an input human body, a custom-shaped garment associated with a clothing type by mapping, via the clothing deformation model, body shape parameters of the input human body to clothing shape parameters of the clothing type and dresses the input human body with the custom-shaped garment.

Abstract: A medical image system (100)for enables a user to navigate through three-dimensional 3D image data showing an anatomical structure by simultaneously displaying a set of views of the 3D image data showing the anatomical structure. The system includes a data input (140) for receiving orientation data (142), a user input (120) for receiving a navigation command (122)from the user, a plane processor (160) for, in dependence on the navigation command, adjusting a spatial configuration of a set of planes (102) for obtaining a further set of planes (162) intersecting the 3D image data, and a view processor (180) for, in dependence on the further set of planes and the orientation data, establishing a further set of views (182) of the 3D image data for displaying the further set of views as an update of the set of views.

Abstract: Ray tracing systems process rays through a 3D scene to determine intersections between rays and geometry in the scene, for rendering an image of the scene. Ray direction data for a ray can be compressed, e.g. into an octahedral vector format. The compressed ray direction data for a ray may be represented by two parameters (u,v) which indicate a point on the surface of an octahedron. In order to perform intersection testing on the ray, the ray direction data for the ray is unpacked to determine x, y and z components of a vector to a point on the surface of the octahedron. The unpacked ray direction vector is an unnormalized ray direction vector. Rather than normalizing the ray direction vector, the intersection testing is performed on the unnormalized ray direction vector. This avoids the processing steps involved in normalizing the ray direction vector.

Abstract: This present disclosure relates to systems and processes for interpolating images of an object from a multi-directional structured image array. In particular embodiments, a plurality of images corresponding to a light field is obtained using a camera. Each image contains at least a portion of overlapping subject matter with another image. First, second, and third images are determined, which are the closest three images in the plurality of images to a desired image location in the light field. A first set of candidate transformations is identified between the first and second images, and a second set of candidate transformations is identified between the first and third images. For each pixel location in the desired image location, first and second best pixel values are calculated using the first and second set of candidate transformations, respectively, and the first and second best pixel values are blended to form an interpolated pixel.

Abstract: Methods for improving movement animation of a model in a simulation are provided. In one aspect, a method includes receiving a movement input for the model, the model includes interconnected joints having respective current locations. Updated locations for each joint are determined based on the movement input and the current locations. Modified locations for each joint are determined based on parameters of a control loop that introduces an error between the current locations and the updated locations. The model is rendered based on the modified locations. Systems and machine-readable media are also provided.

Abstract: Various embodiments of the present invention relate generally to systems and processes for interpolating images of an object. According to particular embodiments, a sequence of images is obtained using a camera which captures the sequence of images along a camera translation. Each image contains at least a portion of overlapping subject matter. A plurality of keypoints is identified on a first image of the sequence of images. Each keypoint from the first image are kept track of to a second image. Using a predetermined algorithm, a plurality of transformations are computed using two randomly sampled keypoint correspondences, each of which includes a keypoint on the first image and a corresponding keypoint on the second image. An optimal subset of transformations is determined from the plurality of transformations based on predetermined criteria, and transformation parameters corresponding to the optimal subset of transformations is calculated and stored for on-the-fly interpolation.

Abstract: The invention notably relates to a computer-implemented method for rendering the global illumination of a three-dimensional scene. The method comprises providing a 3D scene that comprises of a set of triangles and one or more direct light sources, determining that each triangle of the set has an area that is below a threshold, assigning to each triangle of the set a radius of influence using a probability law, obtaining a subset of triangles by filtering out the triangles according to their radius of influence, rendering the three-dimensional scene by lighting its set of triangles, the triangle of the subset of triangles being used as indirect light sources according to their radius of influence.

Abstract: A computer-implemented method for performing compressive sensing of light transport matrix includes receiving a 3D dataset comprising image volume data and randomly selecting a plurality of points on a space curve traversing the 3D dataset. A light transport matrix comprising a plurality of light transmittance values is calculated. Each light transmittance value corresponds to light transmittance between a pair of points included in the plurality of points. An optimization problem is solved to determine a plurality of sparse coefficients which reproduce the light transport matrix when the sparse coefficients are multiplied by a predetermined dictionary of basis vectors. Once determined, the sparse coefficients are stored on a computer-readable medium.

Abstract: By scheduling/managing workload submission to a position only shading pipe one can exploit parallelism with minimum impact to the software scheduler in some embodiments. An interface submits workloads to a slave engine running in one parallel pipe to assist a main engine running in another parallel pipe. Command sequences for each parallel pipe are separated to enable the slave engine to run ahead of the main engine. The slave engine is a position only shader and the main engine is a render engine.

Abstract: A texture processing apparatus for performing filtering by using a plurality of textures. A controller is configured to obtain a first texel value from a memory, in which the first texel value is based on a computed first texel offset value. The previously-computed first texel offset value may be used as a second texel offset value to obtain a second texel value of a second texture if a same texture address is input with respect to the first texture and the second texture that are continuously input. A texture filter is configured to perform filtering based on the obtained texel value of the first texture and the texel value of the second texture.

Abstract: An apparatus for generating 3-dimensional (3D) volume mask model and a method therefor. The apparatus includes a 2D mask data collector, a 3D mask model generator, and a 3D mask model adjuster, whereby 2D mask data is generated from a 2D mask image designed by a user, a 2D mask mesh is created based on inner and outer contour feature points, a 2D mask is transformed into a 3D model according to the user's settings, and the generated 3D mask model is modified to fit on a facial shape of a person who will wear the mask, and a 3D mask volume model is generated, which is immediately printed by a 3D printer to produce a 3D mask.

Abstract: A method of executing a graphics pipeline includes calculating, while executing the graphics pipeline on a current frame, a resource for processing properties of an object included in a following frame, determining, based on a result of the calculating, whether to perform a pre-process for the object included in the following frame, performing the pre-processing, when the pre-process is determined to be performed, comprising transforming the properties of the object that are to be processed in a graphics pipeline for the following frame, and executing, when the pre-process is to be performed, the graphics pipeline for the following frame by using the transformed properties of the object.