Abstract: An image rendering device realizes stereoscopic viewing of composite images generated by compositing background three-dimensional models and foreground three-dimensional models each defined in three-dimensional modeling space. A texture mapping unit converts background image data into two or more viewpoint textures and maps each viewpoint texture to a background three-dimensional model in the three-dimensional modeling space. A viewport conversion unit extracts, for each of the two or more viewpoint textures, a viewport image from the background three-dimensional model mapped with the viewpoint texture and from the foreground three-dimensional model.

Abstract: An image processing device configured to be installed in a vehicle includes an image acquirer, an image selector, a first luminance adjuster, a synthetic image generator, and an image provider. The image acquirer acquires camera images captured by cameras provided on the vehicle. The image selector selects one of the camera images as a representative image based on luminances of the camera images. The first luminance adjuster adjusts a luminance of at least one of the other camera images based on a luminance of the representative image. The synthetic image generator generates a synthetic image showing a periphery of the vehicle, based on the representative image and the other camera images the luminance of at least one of which has been adjusted by the first adjuster. The image provider outputs, to a display device installed in the vehicle, information corresponding to the synthetic image.

Abstract: Embodiments of the present invention relate to displaying and navigating within photo placemarks in a geographic information system. In an embodiment, a method registers a photographic image in a geographic information system. A location of the photographic image within geographic information of the geographic information system is determined based on the geographic information and a metadata of the photographic image. The location of the photographic image is stored.

Abstract: Perceptually correct noises simulating a variety of noise patterns or textures may be applied to stereo image pairs each of which comprises a left eye (LE) image and a right eye (RE) image that represent a 3D image. LE and RE images may or may not be noise removed. Depth information of pixels in the LE and RE images may be computed from, or received with, the LE and RE images. Desired noise patterns are modulated onto the 3D image or scene so that the desired noise patterns are perceived to be part of 3D objects or image details, taking into account where the 3D objects or image details are on a z-axis perpendicular to an image rendering screen on which the LE and RE images are rendered.

Abstract: Technologies are generally described for generating depth data based on a spatial light pattern. In some examples, a method of generating depth data includes obtaining an image of one or more objects on which a spatial light pattern is projected, wherein blurring of the spatial light pattern in the image monotonously increases or decreases in a depth direction, calculating a value of a spatial frequency component of the image in a local image area around a pixel of interest, and determining depth data corresponding to the calculated value of the spatial frequency component by utilizing a preset relationship between depths and values of the spatial frequency component.

Abstract: Systems and methods for reconstructing a floorplan of a building for generating a three-dimensional model are provided. One aspect of the present disclosure is directed to a computer-implemented method for generating a three-dimensional model of a building. The method includes estimating a floor height and a ceiling height of the building. The method also includes identifying a core region of a two-dimensional graph, the core region corresponding to an interior of the building. The method includes determining a solution path that circumnavigates the core region and minimizes a cost formula, the cost formula providing an edge cost for each of a plurality of edges. The method further includes generating a three-dimensional model of the interior of the building based on the floor height, the ceiling height, and the solution path.

Abstract: A document that includes a representation of a two-dimensional (2-D) image may be obtained. A selection indicator indicating a selection of at least a portion of the 2-D image may be obtained. A match correspondence may be determined between the selected portion of the 2-D image and a three-dimensional (3-D) image object stored in an object database, the match correspondence based on a web crawler analysis result. A 3-D rendering of the 3-D image object that corresponds to the selected portion of the 2-D image may be initiated.

Abstract: An image processing method and system using the same, wherein the image processing method includes capturing a plurality of images corresponding to the surroundings of an object using a plurality of image capturing modules to generate a two-dimension planar image; providing a three-dimension projected curved surface; defining a plurality of first grids on the three-dimension projected curved surface and a plurality of second grids on the two-dimension planar image, wherein each of the first grids correspond to each of the second grids; transforming the first grids on the three-dimension projected curved surface and the second grids on the two-dimension planar image into a plurality of first redrawn grids and second redrawn grids respectively based on the angles formed between the normal vector of the two-dimension planar image and the normal vector of each first grid, wherein each first redrawn grid corresponds to each second redrawn grid.

Abstract: A method for a computer system including receiving a file comprising textures including a first and a second texture map, which can be regular or irregular texture maps, and metadata, wherein the metadata includes identifiers associated with texture maps and includes adjacency data, associating the first texture map with a first face of an object in response to an identifier associated with the first texture map, associating the second texture map with a second face of the object in response to an identifier associated with the second texture map, determining an edge of the first texture map is adjacent to an edge of the second texture map in response to the adjacency data, and performing a rendering operation with respect to the first and second faces of the object to determine rendering data in response to the first and second texture maps.

Abstract: A method for determining a 4D plan for carrying out intensity-modulated radiation therapy of a target volume subject to irregular periodic motion, with a radiation therapy apparatus is provided. The method includes selecting positions of a radiation source. The number of positions is selected to be identical in all 3D radiation therapy plans. The method also includes selecting a number of respective aperture settings assigned to a respective position of the radiation source to be identical in all 3D radiation therapy plans. A geometrical, temporal, and/or dynamic restriction that restricts a change of the aperture from one aperture setting to another aperture setting is predetermined, and the 3D radiation therapy plans are determined such that the 3D radiation therapy plans fulfill predetermined restrictions for aperture settings in each case.

Abstract: A system for real-time stereo matching is provided, which provides improved stereo matching speed and rate by gradually optimizing a disparity range used in the stereo matching based on the stereo matching result of the previous frame image and thus reducing unnecessary matching computations.

Abstract: A method for providing a LUT for changing color components of pixels of an image includes generating N two-dimensional slices from a three-dimensional LUT. The N two-dimensional slices are arranged in order from a first two-dimensional slice to an Nth two-dimensional slice. The method includes generating N upsampled slices corresponding to the N two-dimensional slices. The N upsampled slices are arranged in order from a first upsampled slice to an Nth upsampled slice. The method includes forming a first group of slices comprising the N upsampled slices, and forming a second group of slices comprising a second two-dimensional slice of the N two-dimensional slices through the Nth two-dimensional slice and a copy of the Nth two-dimensional slice. The method includes storing the first group of slices and the second group of slices, respectively, in a zero level of a mip map and a first level of the mip map.

Abstract: Disclosed are a system for making 3D contents provided with visual fatigue minimization and a method of the same. More particularly, an exemplary embodiment of the present invention provides a system for making 3D contents including: a human factor information unit generating guide information for making 3D contents by considering factors causing visual fatigue of the 3D contents; and a 3D contents making unit applying guide information generated by the human factor information unit to 3D contents data inputted for making the 3D contents to make the 3D contents, and a method of making 3D contents.

Abstract: There is provided an image composition apparatus including a parallax deriving unit configured to derive a parallax of one area in a background image, the one area corresponding to one object in the background image, an image selection unit configured to select an image which has a parallax different from the parallax of the one area in the background image, as a material image, from a plurality of three-dimensional images, each of which is viewed as a specific object in a three-dimensional manner, and an image composition unit configured to superpose the material image selected by the image selection unit on the background image.

Abstract: Systems and methods are provided for resolving seams in computer graphics when a two-dimensional image is applied to a three-dimensional structure. The method can include providing a two-dimensional image in a UV space, identifying at least one sub-image on the two-dimensional image, defining a seam connectivity for the two-dimensional image in the UV space, and remapping the location of an object on the two-dimensional image when the location of the object is within at least one seam boundary of the seam map.

Abstract: Systems, methods, and apparatus, including computer program products, are provided for forming composite images. In some implementations, a method is provided. The method includes receiving a set of component images for forming a composite image and defining a first projection for the set of component images corresponding to a first reference frame. The method also includes identifying a plane corresponding to a point of view of the set of component images, where a normal to the plane corresponds to a second reference frame, defining a second projection for the set of component images corresponding to the second reference frame, the second reference frame corresponding to a rotation from the first reference frame defined using the normal of the identified plane, and rendering the composite image according to the second projection.

Abstract: A chart generation unit generates an adjustment chart, and a projection unit projects the adjustment chart onto a circular cylinder. A parameter acquiring unit acquires 12 parameters in total, relating to the positions of four corners and middle points of a top side and a bottom side of a chart and lateral expansion of the chart, the chart being input by a user through manipulations of an operation unit. A transform function determination unit calculates, from the total of 12 parameters, an accurate transform function for projecting an image onto the circular cylinder. An image conversion unit applies geometric transformation to the image based on the calculated transform function.

Abstract: The present invention provides an improved method and device for generating a depth map (112) by extracting three-dimensional depth information from the movement vectors of an encoded video bit stream (102) to display two-dimensional video sequences onto three-dimensional displays. In particular, the invention performs depth extraction (110) by means of a post-processing of the movement vectors of the inter-coded macroblocks, which have been already encoded in the video bit stream, thereby significantly reducing the heavy processing requirements associated with conventional motion estimation techniques.

Abstract: A system that incorporates teachings of the exemplary embodiments may include, for example, means for generating a disparity map based on a depth map, means for determining accuracy of pixels in the depth map where the determining means identifies the pixels as either accurate or inaccurate based on a confidence map and the disparity map, and means for providing an adjusted depth map where the providing means adjusts inaccurate pixels of the depth map using a cost function associated with the inaccurate pixels. Other embodiments are disclosed.

Abstract: The invention provides, in some aspects, a system for implementing a rule derived basis to display image sets. In various embodiments of the invention, the selection of the images to be displayed, the layout of the images, as well as the rendering parameters and styles can be determined using a rule derived basis. In an embodiment of the present invention, the user is presented with images displayed based on their preferences without having to first manually adjust parameters.

Abstract: Photographic images can be used to enhance three-dimensional (3D) virtual models of a physical location. In an embodiment, a method of generating a 3D scene geometry includes obtaining a first plurality of images and corresponding distance measurements for a first vehicle trajectory; obtaining a second plurality of images and corresponding distance measurements for a second vehicle trajectory, the second vehicle trajectory intersecting the first vehicle trajectory; registering a relative vehicle position and orientation for one or more segments of each of a first vehicle trajectory and a second vehicle trajectory; generating a three-dimensional geometry for each vehicle trajectory; mapping the three-dimensional geometries for each vehicle trajectory onto a common reference system based on the registering; and merging the three-dimensional geometries from both trajectories to generate a complete scene geometry.

Abstract: A structure for determining a plane in a depth image includes dividing a portion of a depth image into a plurality of areas, fitting a two-dimensional line to depth points in each of the plurality of areas, and combining two or more of the plurality of two-dimensional lines to form a three-dimensional plane estimate.

Abstract: A method and non-transitory program for determining a plane in a depth image includes dividing a portion of a depth image into a plurality of areas, fitting a two-dimensional line to depth points in each of the plurality of areas, and combining two or more of the plurality of two-dimensional lines to form a three-dimensional plane estimate.

Abstract: For generating a 3D geometric model (44) and/or a definition of the 3D geometric model from a single digital image of a building facade (4), a facade structure is detected from the digital image by dividing the facade (4) along horizontal lines into horizontal layers representative of floors (41), and by dividing the horizontal layers along vertical lines into tiles (42). The tiles (42) are further subdivided into a hierarchy of rectangular image regions (43). 3D architectural objects (45) corresponding to the image regions (43) are determined in an architectural element library. The 3D geometric model (44) or the definition of the 3D geometric model is generated based on the facade structure, the hierarchy and the 3D architectural objects (45). The library-based generation of the 3D geometric model makes it possible to enhance simple textured building models constructed from aerial images and/or ground-based photographs.

Abstract: A method for modeling blood flow through a flow diverter includes receiving a medical image containing blood vessels. Vessel geometry is extracted from the received medical image. Inlets and outlets are tagged within the extracted vessel geometry. A desired flow diverter is selected. A model of the selected flow diverter is generated within the imaged blood vessel, the model representing the flow diverter as a tube having a porous surface characterized by a viscous resistance and an inertial resistance. A course of blood flow though the flow diverter is predicted based on the generated model, the extracted vessel geometry, and the tagged inlets and outlets.

Abstract: The present invention discloses a contactless 3D biometric feature identification system and the method thereof. The system comprises of a fixed-viewpoint image capturing means, a lighting module capable of producing different illuminations on the object of interest and a microprocessor configured to execute a biometric identification algorithm. The algorithm starts with capturing a plurality of images with different illuminations. The captured images are then utilized to reconstruct a three dimensional surface model. Different features, for instance 2D and 3D coordinates and orientations of the biometric feature, surface curvature of the object and the local surface orientation of the object, are extracted from the captured images and the reconstructed 3D surface model. Different matching scores are also developed based on the aforesaid features to establish the identity of the biometric features.

Abstract: Systems and methods for providing a view of a digital slide image. In an embodiment, a digital slide image file is accessed. The digital slide image file may comprise a plurality of first image planes representing an image of at least a portion of a slide specimen at varying focal depths. Then, a three-dimensional object is constructed from the digital slide image file. The three-dimensional image object comprises a plurality of second image planes that are derived from one or more of the first image planes and may comprise at least one image plane that has been interpolated from one or more of the first image planes. In addition, a two-dimensional and/or three-dimensional view of the three-dimensional object may be generated.

Abstract: A system uses range and Doppler velocity measurements from a lidar system and images from a video system to estimate a six degree-of-freedom trajectory (6DOF) of a target. The 6DOF transformation parameters are used to transform multiple images to the frame time of a selected image, thus obtaining multiple images at the same frame time. These multiple images may be used to increase a resolution of the image at each frame time, obtaining the collection of the superresolution images.

Abstract: A parallax representation unit in a displayed image processing unit uses a height map containing information on a height of an object for each pixel to represent different views caused by the height of the object. A color representation unit uses, for example, texture coordinate values derived by the parallax representation unit to render the image, shifting the pixel defined in the color map. The color representation unit uses the normal map that maintains normals to the surface of the object for each pixel to change the way that light impinges on the surface and represent the roughness accordingly. A shadow representation unit uses a horizon map, which maintains information for each pixel to indicate whether a shadow is cast depending on the angle relative to the light source, so as to shadow the image rendered by the color representation unit.

Abstract: In a method for fluoroscopy controlled insertion of a stent into a curved aorta for aneurysm repair, a 3D volume image is obtained of a patient's aorta at the aneurysm. By knowing a registration of the 3D volume image to a C-arm of an angiographic system and projection geometry of the angiography system, the 3D volume images are projected to a 2D fluoroscopy image of the angiography system. For the 2D3D overlay, the 3D volume image is displayed as a curved planar reconstruction in which the 2D fluoroscopy image and the 3D volume image are warped around a curved center line of the curved aorta or around a curved guide instrument center line to correct for the curvature of the aorta so that the previously curved aorta center line or curved center line of the guide instrument turns into a straight line to visualize insertion of the stent.

Abstract: A system and method for providing an augmented reality environment in which the environmental mapping process is decoupled from the localization processes performed by one or more mobile devices is described. In some embodiments, an augmented reality system includes a mapping system with independent sensing devices for mapping a particular real-world environment and one or more mobile devices. Each of the one or more mobile devices utilizes a separate asynchronous computing pipeline for localizing the mobile device and rendering virtual objects from a point of view of the mobile device. This distributed approach provides an efficient way for supporting mapping and localization processes for a large number of mobile devices, which are typically constrained by form factor and battery life limitations.

Abstract: A method of performing motion compensation includes dividing a current frame of video data into blocks, and clustering the blocks based on motion vectors.

Abstract: A method of converting a two-dimensional video to a three-dimensional video, the method comprising: comparing an image of an nth frame with an accumulated image until an n?1th frame in the two-dimensional video to calculate a difference in a color value for each pixel; generating a difference image including information on a change in a color value for each pixel of the nth frame; storing an accumulated image until the nth frame by accumulating the information on the change in the color value for each pixel until the nth frame; performing an operation for a pixel in which a change in a color value is equal to or larger than a predetermined level by using the difference image to generate a division image and a depth map image; and converting the image of the nth frame to a three-dimensional image by using the depth map image.

Abstract: Field of view overlap among multiple cameras is automatically determined as a function of the temporal overlap of object tracks determined within their fields-of-view. Object tracks with the highest similarity value are assigned into pairs, and portions of the assigned object track pairs having a temporally overlapping period of time are determined. Scene entry points are determined from object locations on the tracks at a beginning of the temporally overlapping period of time, and scene exit points from object locations at an ending of the temporally overlapping period of time. Boundary lines for the overlapping fields-of-view portions within the corresponding camera fields-of-view are defined as a function of the determined entry and exit points in their respective fields-of-view.

Abstract: Various aspects of a method and apparatus for video processing may include a computing device communicably coupled to an external device. The computing device may be operable to determine an average vertical velocity and an average horizontal velocity of a subset of pixels in an image frame and determine a depth value for each pixel of the subset of pixels based on calculated motion vectors of the pixel of the subset of pixels, the average vertical velocity of the subset of pixels and the average horizontal velocity of the subset of pixels.

Abstract: A driving simulation apparatus includes an input unit that receives an input of an operation instruction, a vehicle simulation unit that calculates a position and an orientation of a vehicle in a virtual environment in real-time, a camera state calculation unit that calculates a viewpoint position and a viewing direction of a on-vehicle wide-angle camera based on the position and the orientation of the vehicle, and a wide-angle camera simulation unit.

Abstract: A method (and system) of processing image data in which a depth map is processed to derive a modified depth map by analyzing luminance and/or chrominance information in respect of the set of pixels of the image data. The depth map is modified using a function which correlates depth with pixel height in the pixelated image and which has a different correlation between depth and pixel height for different luminance and/or chrominance values.

Abstract: A method for a computer system includes receiving a surface deformation for an object from a computer system user, wherein an object model comprises animation variables used to determine the surface of the object model, determining at least one pre-defined object pose from pre-defined object poses in response to the surface deformation, wherein the predefined object poses includes a first predefined object pose and comprises animation variable values, wherein the animation variable values are determined from physical motion capture data of surface positions of a physical representation of the object posed in a first pose, posing the object model in a pose in response to at least the animation variable values, and displaying the object model in the pose on a display to the computer system user.

Abstract: An image processing system in which the georeferencing of at least one digital image is achieved by means of at least one picture model of the said digital image and of a digital reference relief form. The digital image is obtained from a pair of digital images acquired in the same focal plane. An intermediate digital relief form is produced from said pair of digital images. The intermediate digital relief form and said digital reference relief form are processed to refine the said picture model of the said digital image to be georeferenced. A final digital relief form is generated and said final digital relief form and said digital image are projected in a geographical or cartographic system, for the purpose of their georeferencing. The pair of digital images in the same focal plane are acquired in a small stereoscopic base configuration by sensors located in the same focal plane.

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: The system includes a module to receive data representing media content, such as a video image, a photograph, and an audio or video file, each being of a first dimension. An encoding module encoded the received data using a parametric number representation system, such a Multiple Base Number System, which includes a combination of fused numerical representation system. A decomposing module decomposes the encoded data into a plurality of signals or slices. A generating module to take the decomposed data and generates data representing the media content in a second dimension that is of a higher order that the first dimension. An output module to output a media representation of the generated higher order data. The media, by way of example could be a 3D image of a received 2D image.

Abstract: An apparatus for correcting a stereoscopic image using matching information, includes: a matching information visualizer receiving input of original stereoscopic images and intuitive matching information and visualizing a pair of stereoscopic images based on the intuitive matching information; a correction information processor obtaining a statistical camera parameter based on the intuitive matching information and correcting the received stereoscopic image using the statistical camera parameter; and an error allowable controller providing allowable error information to the correction information processor in consideration of an error allowable degree according to a selected time from the received intuitive matching information and preset human factor guide information, to extract a correlation between stereoscopic images using a stereoscopic image and provided information, thereby helping such that an erroneously photographed image is correctly photographed or correcting the image such that the erroneously p

Abstract: A SLAM of a robot is provided. The position of a robot and the position of feature data may be estimated by acquiring an image of the robot's surroundings, extracting feature data from the image, and matching the extracted feature data with registered feature data. Furthermore, measurement update is performed in a camera coordinate system and an appropriate assumption is added upon coordinate conversion, thereby reducing non-linear components and thus improving the SLAM performance.

Abstract: An accurate, flexible and scalable technique for multi-modal image registration is described, a technique that does not need to rely on direct feature matching and does not need to rely on precise geometric models. The methods and/or systems described in this disclosure enable the registration (fusion) of multi-modal images of a scene with a three dimensional (3D) representation of the same scene using, among other information, viewpoint data from a sensor that generated a target image, as well as 3D-GeoArcs. The registration techniques of the present disclosure may be comprised of three main steps, as shown in FIG. 1. The first main step includes forming a 3D reference model of a scene. The second main step includes estimating the 3D geospatial viewpoint of a sensor that generated a target image using 3D-GeoArcs. The third main step includes projecting the target image's data into a composite 3D scene representation.

Abstract: Provided is a single repository for capturing, connecting, sharing, and visualizing information based on a geographic location, for example. Provided is a schema, repository, index, and APIs for any information, place, entity, attribute, service or person that can be referenced geographically. A system to provide real time image data includes an input component that receives image data associated with a specific geographic area, a splitter component that splits the image data into at least two quadrants, and a storage component that stores at least a portion of the at least two quadrants. Also provides is on-line or real-time advertising based on a user's mapped location and/or a user preference.

Abstract: Described is a system for multiple-object recognition in visual images. The system is configured to receive an input test image comprising at least one object. Keypoints representing the object are extracted using a local feature algorithm. The keypoints from the input test image are matched with keypoints from at least one training image stored in a training database, resulting in a set of matching keypoints. A clustering algorithm is applied to the set of matching keypoints to detect inliers among the set of matching keypoints. The inliers and neighboring keypoints in a vicinity of the inliers are removed from the input test image. An object label and an object boundary for the object are generated, and the object in the input test image is identified and segmented. Also described is a method and computer program product for multiple-object recognition in visual images.

Abstract: A system and method for finding real terrain matches in a stereo image pair is presented. A method for finding differences of underlying terrain between a first stereo image and a second stereo image includes performing epipolar rectification on a stereo image pair to produce rectified image data. The method performs a hybrid stereo image matching on the rectified image data to produce image matching data. A digital surface model (DSM) is generated based on the image matching data. Next, the method identifies areas in the DSM where the stereo image matching should fail based on the image matching data and the DSM to generate predicted failures. The method can then determine real terrain changes based on the predicted failures and the image matching data.

Abstract: A hierarchical pattern matching process is improved for use in three-dimensional reconstruction by calculating a disparity field for low-resolution data, and using this low-resolution disparity field to estimate the disparity field for higher-resolution images. By pre-warping a template according to the estimated disparity field, improved correlation results can be obtained.

Abstract: Three dimensional models corresponding to a target image and a reference image are selected based on a set of feature points defining facial features in the target image and the reference image. The set of feature points defining the facial features in the target image and the reference image are associated with corresponding 3-dimensional models. A 3D motion flow between the 3-dimensional models is computed. The 3D motion flow is projected onto a 2D image plane to create a 2D optical field flow. The target image and the reference image are warped using the 2D optical field flow. A selected feature from the reference image is copied to the target image.

Abstract: The present invention provides methods and apparatus for generating a three dimensional output which includes a continuum of image data sprayed over three-dimensional models. The three-dimensional models can be representative of features captured by the image data wherein image data can be captured at multiple disparate points along another continuum. The user interface can also include multiple modalities of image data and statistical analysis of the image data.