Abstract: A machine learning model is trained and used to perform a computer vision task such as semantic segmentation or normal direction prediction. The model uses a current image of a physical setting and input generated from three dimensional (3D) anchor points that store information determined from prior assessments of the physical setting. The 3D anchor points store previously-determined computer vision task information for the physical setting for particular 3D points locations in a 3D worlds space, e.g., an x, y, z coordinate system that is independent of image capture device pose. For example, 3D anchor points may store previously-determined semantic labels or normal directions for 3D points identified by simultaneous localization and mapping (SLAM) processes. The 3D anchor points are stored and used to generate input for the machine model as the model continues to reason about future images of the physical setting.

Abstract: A binary logic circuit for performing an interpolation calculation between two endpoint values E0 and E1 using a weighting index i for generating an interpolated result P, the values E0 and E1 being formed from Adaptive Scalable Texture Compression (ASTC) low-dynamic range (LDR) colour endpoint values C0 and C1 respectively, the circuit comprising: an interpolation unit configured to perform an interpolation between the colour endpoint values C0 and C1 using the weighting index i to generate a first intermediate interpolated result C2; and combinational logic circuitry configured to receive the interpolated result C2 and to perform one or more logical processing operations to calculate the interpolated result P according to the equation P=?((C2<<8)+C2+32)/64? when the interpolated result is not to be compatible with an sRGB colour space, and according to the equation P=?((C2<<8)+128.64+32)/64? when the interpolated result is to be compatible with an sRGB colour space.

Abstract: A binary logic circuit for performing an interpolation calculation between two endpoint values E0 and E1 using a weighting index i for generating an interpolated result P, the values E0 and E1 being formed from Adaptive Scalable Texture Compression (ASTC) colour endpoint values C0 and C1 respectively, the colour endpoint values C0 and C1 being low-dynamic range (LDR) or high dynamic range (HDR) values, the circuit comprising: an interpolation unit configured to perform an interpolation between the colour endpoint values C0 and C1 using the weighting index i to generate a first intermediate interpolated result C2; combinational logic circuitry configured to receive the interpolated result C2 and to perform one or more logical processing operations to calculate the interpolated result P according to the equation: (1) P=?((C2«8)+C2+32)/64? when the interpolated result is not to be compatible with an sRGB colour space and the colour endpoint values are LDR values; (2) P=?((C2«8)+128.

Abstract: An image display method executes on an electronic device.

Abstract: A measurement device adapted to cooperate with a three-dimensional image is provided. The three-dimensional image includes a plurality of three-dimensional positioning points. The measurement device comprises: a first camera unit for providing a two-dimensional image; an analysis module for analyzing the two-dimensional image to define a plurality of two-dimensional positioning points; a matching module for making the two-dimensional positioning points correspond to the three-dimensional positioning points, respectively, to generate a three-dimensional model; an input module for receiving a starting point and a destination in the two-dimensional image; a measurement module for obtaining first position information and second position information that correspond to the starting point and the destination respectively and calculating data; and an output module. A processor configured to execute a measurement method is also provided.

Abstract: A method for generating a panoramic image includes providing a 3D point model of an area surrounding a virtual viewpoint, acquiring multiple images of the area surrounding the virtual viewpoint, projecting the acquired images onto the 3D point model and generating the panoramic image using the thus obtained 3D point model of the surrounding area.

Abstract: The present disclosure provides for methods, systems and instruments for creating a partial model of a head for use in planning or tracking a procedure, such as hair transplantation. The methodology allows for an accurate 3D representation to be quickly and efficiently generated of an identified portion of the head, not the entire head, from two or more 2D images, such as still images. According to the methodology of the present disclosure a 3D dome representation of the top portion of the head of a subject may be created based on the data extracted from one or more 2D images and/or a certain determined height dimension.

Abstract: Techniques and systems are described to generate a three-dimensional model from two-dimensional images. A plurality of inputs is received, formed through user interaction with a user interface. Each of the plurality of inputs define a respective user-specified point on the object in a respective one of the plurality of images. A plurality of estimated points on the object are generated automatically and without user intervention. Each of the plurality of estimated points corresponds to a respective user-specified point for other ones of the plurality of images. The plurality of estimated points is displayed for the other ones of the plurality of images in the user interface by a computing device. A mesh of the three-dimensional model of the object is generated by the computing device by mapping respective ones of the user-specified points to respective ones of the estimated points in the plurality of images.

Abstract: A digital signal processor 1 is provided for performing digital image processing operations such as forward texture mapping. A first logic unit 21 receives input sample coordinates xr and xl, and determines a first color weight value “w” and a second color weight value “wN”. A second logic unit 23 weights an input sample color with the color weight value wN, with the resultant weighted sample color being added to accumulated weighted sample colors from one or more previous iterations, thereby producing a new accumulated weighted sample color, ie the rgbaPartOut signal 13. A third logic unit 25 is configured to weight the input sample color with the first color weight value w, with the resultant weighted sample color being added to the accumulated weighted sample colors rgbaPartIn to produce the output color signal rgbaOut 11.

Abstract: A portable pervasive device includes a combined visual and thermal display. The user is able to detect texture of displayed objects visually and through touching the combined display. A software application pre-defines color codes and temperature settings for a plurality of textures on a graded scale including smooth, soft, and rough. The object is then shown on the display using the color codes and temperature settings for at lest one surface of the object.

Abstract: A method of operating a three-dimensional (3D) map system including: receiving an image and a geo-location tag of the image; determining a building model for a physical building corresponding to an object captured in the image based on the geo-location tag; mapping, on a region-by-region basis, the image to a stored facade of the building model; and mapping, on a pixel-by-pixel basis, the image to the stored facade of the building model for displaying the image as a new facade of the building.

Abstract: Systems and methods are provided for producing a rendered drawing or rendering from a detailed image of an object (e.g. photograph) resulting in a rendering that is photogrammetric and that preserves detail in the said image of said object. The combination of the metric nature and image detail preservation in a rendering resulting from the process enhances the usefulness of the rendering to users. The invention is useful in particular for large format renderings such as wire frame style drawings used for blueprints in the architecture, engineering and construction industry (AEC industry) when used for existing structures. The processes combine graphic arts techniques with photogrammetric techniques to preserve, fully or partially, information about an object as captured in image detail of said object and to present said information in photogrammetrically correct rendering, which rendering may be incorporated into drawings useful to and/or familiar to end users of said drawings.

Abstract: A method for rendering an image on computer system including a display includes determining a first displacement map associated with a surface material and a first input parameter, determining a second displacement map associated with the surface material and a second input parameter. determining a three-dimensional displacement data structure in response to the first displacement map, the first input parameter, the second displacement map and the second input parameter in the computer system, receiving a third input parameter, determining a third displacement map associated with the surface material in response to the three-dimensional displacement data structure and the third input parameter in the computer system, rendering an image of an object in the computer system, wherein an appearance of a surface of the object is determined in response to the third displacement map, and displaying the image on the display to a user.

Abstract: A computer system generates video based cohorts. Digital video data is processed to identify a set of color and texture based attributes associated with clothing worn by a set of objects. The digital video data comprises metadata describing the set of objects. The set of color and texture based attributes are analyzed using cohort criteria to form a result. The cohort criteria specify attributes that are associated with members of a given cohort. A set of cohorts is generated based on the result. Each cohort in the set of cohorts comprises a subset of objects from the set of objects that share at least one color and texture based attribute in common.

Abstract: Provided is an image encoding/decoding method and apparatus. In the image encoding method, a portion of a texture region included in a current picture is selected as a sample texture for synthesizing the texture region and only the sample texture is encoded in place of the texture region, thereby improving the compression efficiency of encoding with respect to the texture region and thus improving the compression efficiency of encoding with respect to the entire image.

Abstract: A method for modifying color data in a display system is implemented using hardware circuitry. The method includes receiving first-color data associated with a first bit depth, the first-color data including a first-color data value. The method also includes receiving second-color data associated with a second bit depth that is less than the first bit depth, the second-color data including a second-color data value that corresponds to the first-color data value. The method also includes normalizing the second-color data according to the first bit depth for generating normalized second-color data. The method also includes adding an offset value to each data value of the normalized second-color data to generate offset second-color data, the offset second-color data including an offset second-color data value that corresponds to the first-color data value. The method also includes determining a modified second-color data value using the first-color data value and the offset second-color data value.

Abstract: A multi-view image may be generated by detecting discontinuities in a radiance function using multi-view silhouette edges. A multi-view silhouette edge is an edge of a triangle that intersects a back tracing plane and, in addition, the triangle faces backwards, as seen from the intersection point, and the edge is not further connected to any back facing triangles. Analytical visibility may be computed between shading points and a camera line and shared shading computations may be reused.

Abstract: A computer-implemented method includes identifying a bit-mapped image of a line or polygon shape; mapping the image to a texture map that is slightly large in at least one dimension than the bit-mapped image; overlaying the bit-mapped image and the texture map; computing pixel shading for pixels between an outer edge of the bit-mapped image and the texture map by measuring a distance from particular ones of the pixels to an idealized line near an edge of the bit-mapped image; and displaying the bit-mapped image with pixels at its edge shaded according to the computed pixel shading.

Abstract: A method of and an apparatus for performing a collision simulation on a two-wheeled vehicle using a virtual model of a dummy developed for use on four-wheeled vehicles.

Abstract: A graphic processing unit (GPU) with a configurable filtering module (CFU) and an operation method thereof are presented. The graphic processing unit comprises a memory module and a configurable filtering module. The memory module stores at least one texture image. The configurable filtering module, connected to the memory module, comprises a plurality of filter equations, from which a filter equation is selected. A plurality of pixel points are sampled from the texture image. Each sampled pixel point is set with a weight value respectively. Each sampled pixel point with a weight value corresponding thereto is substituted into the selected filter equation to perform an operational process to acquire an operated value. Thereby, the user can decide the operation method of the GPU by selecting an appropriate filter equation and setting adjustable parameters in the filter equation.

Abstract: A method for photogrammetric texture mapping using casual images is provided. The method may include the following steps: estimating, for each vertex of at least a portion of a three dimensional (3D) mesh representing a model, projection parameters associated with a virtual camera that is unique for each vertex; mapping pixels from a two dimensional (2D) image to the vertices, such that each mapping of a pixel is based on the estimated respective virtual camera parameters; and texturing the portion of the mesh with corresponding mapped pixels wherein vertices on the textured portion are selected such that they are visible from a specified viewpoint associated with the 3D mesh.

Abstract: Various technologies for a layered texture compression architecture. In one implementation, the layered texture compression architecture may include a texture consumption pipeline. The texture compression pipeline may include a processor, memory devices, and textures compressed at varying ratios of compression. The textures within the pipeline may be compressed at ratios in accordance with characteristics of the devices in the pipeline that contains and processes the textures.

Abstract: Object previews for projection painting operations using arbitrary paint surfaces are provided. The object preview is rendered from the view of the arbitrary projection paint surface. The object preview is provided to the user, who then may define projection paint attribute values by painting over the object preview. The projection paint attribute values are mapped back on to the projection paint surface and one or more images of the object geometry are rendered using the projection paint attribute values. Object previews are rendered by defining a camera view and a proxy surface. A mapping from the proxy surface to a projection surface is defined and associates proxy surface points with projection paint surface points. Rays generated using a projection operation are defined and a renderer uses these rays to determine attribute values for their associated points on the proxy surface to define an object preview image.

Abstract: An embodiment of the invention relates to a method for generating a radiance map in High Dynamic Range (HDR) image creation by calculating mean difference curves for a sequence of images taken with different exposures and a transformation curve from the mean difference curve by an algorithm approximated to the Debevec function, by the means of which a radiance map can be calculated from the taken images. A further embodiment of the invention relates to a unit for performing this method.

Abstract: A procedure for texturing an object of a virtual three-dimensional geometric model represented by three-dimensional geometric model data comprised of a three-dimensional object data associated with the object. Facet data is created out of three-dimensional geometric model data representing object surfaces of an object and which will be assigned 3D object data. Texture data is created representing a surface texture of the object surfaces of each object and which is assigned facet data. The three-dimensional object data, facet data and texture data are used to create a textured, three-dimensional representation of the object.

Abstract: Embodiments of the present invention include techniques for reducing artifacts in rendered images. In one embodiment, a dual UV engine generates a dual of the graph defined by an initial UV set associated with a 3D model. The dual UV engine then uses existing flattening and layout engines to generate a dual UV set from this dual graph. Using the dual graph to define the dual UV set ensures that the seams corresponding to the initial UV set and the dual UV set minimally intersect.

Abstract: A method and apparatus for a navigation system detects a hidden point on a route on a monitor screen showing a three-dimensional map when visibility of the route begins to be lost, and provides a warning message including relevant information that is helpful to navigate the hidden point. The method includes steps of displaying a three-dimensional map image which includes an image of a route on which a user or user's vehicle is travelling, detecting a hidden point of the route on the three-dimensional map image at which the route becomes invisible by an obstruction object when viewed from a current position of the user, and notifying the user about the hidden point on the route thereby enabling the user to know the hidden point on the route in advance.

Abstract: Methods, systems and computer program code (software) products executable in a digital processor operable to generate a synthetic image include (1) selecting a rank-1 lattice in accordance with a maximized minimum distance function (max-min-dist lattice) corresponding to points in the synthetic image to be generated; (2) generating a data structure for efficient access of data stored in points of the rank-1 lattice, the data structure including the number n of lattice points, generator vector g, s basis vectors, and indices of the basis vectors, wherein the basis vectors are lattice points, and (3) generating, using the rank-1 lattice, digital output representative of a synthetic image, wherein the generating includes using the layout of rank-1 lattice points to represent textures of arbitrary dimension.

Abstract: A method and apparatus are disclosed that reduces variation in radiation therapy treatment planning among plurality of users within the same or different geographic locations. The system includes a method and an apparatus that provide users with the knowledge information and utilizing the knowledge information to contour target volumes for radiation treatment planning. The mode of operation includes utilizing a stand-alone workstation or a server computer connected to the plurality of thin client workstations.

Abstract: A graphics processing platform includes a rasteriser 50 that receives primitives representing an image to be displayed for processing. The rasteriser 50 determines which sets of sampling points of the image include sampling points that are covered by a given primitive, and then generates a fragment for rendering for each set of sampling points found to include a sampling point that is covered by the primitive and passes those fragments to a renderer 51 for rendering. The renderer 51 carries out rendering operations on the fragments that it receives, and stores the rendered fragment data in tile buffers 52. The rendered fragment data is stored in multiple copies in the appropriate sample positions in the tile buffers 52, so as to provide a separate set of fragment data for each individual sample position taken of the image. The data from the tile buffers 52 is input to a downsampling unit 53, and hence output to a frame buffer 54 of a display device 55 for display.

Abstract: Systems and methods are provided for producing a rendered drawing or rendering from a detailed image of an object (e.g. photograph) resulting in a rendering that is photogrammetric and that preserves detail in the said image of said object. The combination of the metric nature and image detail preservation in a rendering resulting from the process enhances the usefulness of the rendering to users. The invention is useful in particular for large format renderings such as wire frame style drawings used for blueprints in the architecture, engineering and construction industry (AEC industry) when used for existing structures. The processes combine graphic arts techniques with photogrammetric techniques to preserve, fully or partially, information about an object as captured in image detail of said object and to present said information in photogrammetrically correct rendering, which rendering may be incorporated into drawings useful to and/or familiar to end users of said drawings.

Abstract: The systems and methods described herein provide for fast and accurate image segmentation through the application of a multi-stage classifier to an image data set. An image processing system is provided having a processor configured to apply a multi-stage classifier to the image data set to identify a distinctive region. The multi-stage classifier can include two or more component classifiers. The first component classifier can have a sensitivity level configured to identify one or more target regions in the image data set and the second component classifier can have a specificity level configured to confirm the presence of the distinctive region in any identified target regions. Also provided is a classification array having multiple multi-stage classifiers for identification and confirmation of more than one distinctive region or for the application of different classification configurations to the image data set to identify a specific distinctive region.

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: A subregion-based image parameter recovery system and method for recovering image parameters from a single image containing a face taken under sub-optimal illumination conditions. The recovered image parameters (including albedo, illumination, and face geometry) can be used to generate face images under a new lighting environment. The method includes dividing the face in the image into numerous smaller regions, generating an albedo morphable model for each region, and using a Markov Random Fields (MRF)-based framework to model the spatial dependence between neighboring regions. Different types of regions are defined, including saturated, shadow, regular, and occluded regions. Each pixel in the image is classified and assigned to a region based on intensity, and then weighted based on its classification.

Abstract: Methods and apparatus, including computer program apparatus, implementing techniques for processing digital artwork. In one aspect, the techniques process aggregations of artwork where both the aggregation and at least some of the aggregated artwork have attached styles. The techniques handle various combinations of conditions resulting in applying style elements to the aggregation before or after applying style elements to underlying artwork. In another aspect, the techniques implement editable path objects having multiple attached fills and/or strokes. The techniques provide user interfaces for using the foregoing features.

Abstract: A method allows analyzing and describing the reflective properties of a three-dimensionally structured original surface. The topology of the original surface is determined and the topological data are stored in the form of a depth map in a first data record and evaluated with respect to the influence of the data on the reflective properties. Each surface element is assigned a reflective value in accordance with the evaluation and the value is stored in a second data record and made available to other machining or inspection systems. There, the reflection values of the second data record are divided into classes and the depth values of the first data record, assigned to the classified reflection values, are varied in accordance with the classification. Finally, the changed depth values are employed as parameters for electronically controlling a tool in order to machine the artificially produced surface.

Abstract: A method of automatically transforming a computerized 3D model having regions of images utilized as textures on one or more physical objects represented in the 3D model (such as building sides and roofs, walls, landscapes, mountain sides, trees and the like) to include material property information for one or more regions of the textures of the 3D model. In this method, image textures applied to the 3D model are examined by comparing, utilizing a computer, at least a portion of each image texture to entries in a palette of material entries. The material palette entry that best matches the one contained in the image texture is assigned to indicate a physical material of the physical object represented by the 3D model. Then, material property information is stored in the computerized 3D model for the image textures that are assigned a material palette entry.

Abstract: In a method for determining weighting factors for the color calculation of a color value of texels for a footprint covering a plurality of texels in a texel grid, in a graphic system, form information of the footprint is determined at first. Afterwards, the edges of the footprint are determined and the edges determined in this way are approximated by a staircase function. The texels of the texel grid contacted by the staircase function are determined and a weighting factor is determined for each texel containing a portion of the staircase function, depending on the subarea of the respective texel covered by the footprint.

Abstract: A graphics processing platform includes a rasteriser 50 that receives primitives representing an image to be displayed for processing. The rasteriser 50 determines which sets of sampling points of the image include sampling points that are covered by a given primitive, and then generates a fragment for rendering for each set of sampling points found to include a sampling point that is covered by the primitive and passes those fragments to a renderer 51 for rendering. The renderer 51 carries out rendering operations on the fragments that it receives, and stores the rendered fragment data in tile buffers 52. The rendered fragment data is stored in multiple copies in the appropriate sample positions in the tile buffers 52, so as to provide a separate set of fragment data for each individual sample position taken of the image. The data from the tile buffers 52 is input to a downsampling unit 53, and thence output to a frame buffer 54 of a display device 55 for display.

Abstract: A system, method and computer program product are provided for computer graphics processing. In use, a value is modified based on an algorithm. An operation is subsequently performed on pixel data taking into account the modified value.

Abstract: A face image synthesis apparatus includes a storage device (2) and an arithmetic processing unit (1). The storage device (2) stores a plurality of face images and a plurality of feature points including an origin. The plurality of feature points are set to each of the plurality of face images. The arithmetic processing unit (1) generates a plurality of deformed face images by deforming the plurality of face images so that the origin and the other feature points thereof are matched to each other and generates a synthesized face image from the deformed face images.

Abstract: A method for determining a pose of an object from a range image is presented. A distribution of poses for an object is determined from a model of the object. A set of reference poses is selected according to the distribution, such that more reference poses are selected for more probable poses than less probable poses. A reference image for each reference pose is generated, and the reference pose used to generate the reference image that best matches a range image including the object is assigned as the pose of the object.

Abstract: A system, method and computer program product are provided for retrieving instructions from memory utilizing a texture module in a graphics pipeline. During use, an instruction request is sent to memory utilizing a texture module in a graphics pipeline. In response thereto, instructions are received from the memory in response to the instruction request utilizing the texture module in the graphics pipeline.

Abstract: The center line and lines at the right and left end parts are inputted to a base image from which a texture image is to be mapped, and a position of the base image closest to the view point is inputted as a point closest to the user. Right side of the point closest to the user of the body is approximated by one quarter of circle, and the left side is approximated by another quarter of circle so as to generate an elliptical arc representative of the horizontal cross-sectional shape of the body. The texture image is then mapped to the body using that elliptical arc. Thus mapping of the texture image to the body can be performed easily.

Abstract: The present invention relates to computer graphics applications involving scene rendering using objects modeled at multiple levels of detail. In accordance with an aspect of the invention, a ray tracer implementation allows users to specify multiple versions of a particular object, categorized by LOD ID's. A scene server selects the version appropriate for the particular scene, based on the size of the object on the screen for example, and provides a smooth transition between multiple versions of an object model. In one example, the scene server will select two LOD representations associated with a given object and assign relative weights to each representation. The LOD weights are specified to indicate how to blend these representations together.

Abstract: The present invention relates to an apparatus and a method for rendering volume data in an ultrasound diagnostic system.

Abstract: A system and method are disclosed for generating an animatable object. A skeleton of the desired character is constructed by the user utilizing various predetermined components. These predetermined components include a various selection of rods and joints. The rods are static components which remain rigid during motion, while the various joints are moveable components. A static digitized image, for example, an image of the user, is utilized and a constructed skeleton is superimposed onto it. The desired object, such as the image of the user, can then be extracted from the background of the digital image and the resulting personal character can then be animated, for instance by selecting and dragging one of the hands with a mouse.

Abstract: Apparatus, system, and method for clipping graphics primitives are described. In one embodiment, a graphics processing apparatus includes a clipping engine and an output unit connected to the clipping engine. The clipping engine is configured to clip an input graphics primitive with respect to a set of clipping planes to derive spatial attributes of new vertices. The output unit is configured to identify a subset of the new vertices that defines an output graphics primitive, and the output unit is configured to derive non-spatial attributes of the subset of the new vertices to produce the output graphics primitive.

Abstract: Subsets of volume data are sequentially stored for volume rendering from two dimensional textures. For example, pairs of adjacent two-dimensional images are loaded into RAM or cache. Strips of texture data are interpolated for polygons extending between the two-dimensional images. The strips or polygons are more orthogonal to a viewing direction than the two-dimensional images. After interpolating texture data from the two-dimensional images for a plurality of non-coplanar polygons, the texture data is rendered. The rendered information represents one portion of the three dimensional representation. Other portions are rendered by repeating the process for other pairs or subset groups of adjacent two-dimensional images. A lower cost apparatus, such as a programmed computer or a GPU with a limited amount of memory, is able to render images for three dimensional representations of very large three-dimensional arrays. The images may be rendered without copying volume data for different main axes.

Abstract: A method of generating procedural textures for a plurality of natural phenomena, and an apparatus to perform the method, the method including inputting a set of common parameters required to represent the plurality of natural phenomena; inputting a set of specific parameters required to represent physical properties of at least one of the natural phenomena; generating a noise value using the common parameters and the specific parameters; determining which procedural texture is to be generated according to the common parameters; and generating the procedural texture according to the determination results using the noise value, the common parameters, and the specific parameters.