Abstract: Systems and methods for ray tracing acceleration structure level of detail processing are described. An example graphics processing system is to retrieve a first level of detail value for a sub-tree from a level of detail residency map corresponding to a bounding volume hierarchy of objects. The graphics processing system is to determine a second level of detail value for the sub-tree. The graphics processing system is to select a final level of detail value for the sub-tree based on a comparison between the first level of detail value for the sub-tree and the second level of detail value for the sub-tree. The graphics processing system is to, based on the final level of detail value for the sub-tree, select child nodes in an acceleration structure tree and trace the selected child nodes.

Abstract: The present technology relates to an information processing device, an information processing method, and a program causing a user to be able to appropriately select a fashion item. An information processing device includes a display control unit configured to control display of try-on images including images in which fashion items are superimposed on a user trying on try-on items corresponding to the fashion items. The information processing device is provided in, for example, a moving object such as a cart. The present technology can be applied to, for example, a system that performs electronic commerce of a fashion system.

Abstract: Two-dimensional compositing that preserves the curvatures of non-flat surfaces is disclosed. In some embodiments, a mapping is associated with a two-dimensional rendering that maps a potentially variable portion of the two-dimensional rendering to a canvas. The mapping is generated from a three-dimensional model of the potentially variable portion of the two-dimensional rendering. The potentially variable portion of the two-dimensional rendering is dynamically modified according to the mapping to reflect content comprising the canvas or edits received with respect to the canvas.

Abstract: According to an example embodiment, a method and an apparatus for simulating a garment may receive, through a user interface expressing a three-dimensional (3D) garment, an input of deforming at least one style line among a plurality of style lines representing a style of the 3D garment, identify a first line corresponding to the style line among a plurality of lines included in a two-dimensional (2D) pattern corresponding to the 3D garment, deform the first line based on the input, deform the 2D pattern by propagating deformation of the first line to candidate lines associated with the first line, and output at least one of the deformed 2D pattern and the 3D garment in which the style line is deformed based on the deformed 2D pattern.

Abstract: An Augmented Reality (AR) and Artificial Intelligence (AI) based interactive virtual try-on solution that facilitates trying on, fitting, and modularizing a virtual apparel in real-time—as if a consumer were wearing the apparel. A user with a mobile device defines retail adjustment operations on the virtual apparel using an AR-based visual interface. The user can interact with the virtual apparel for identifying, defining, and changing the look, fit, and design of the apparel on the user's body. The real-time interaction is with the same virtual apparel. The system defines operations based on user's features, sartorial measurements, intent, gestures, position, pressure values received from a controller operated by the user, and the sensed motion of the user to translate into a set of machine learning inference models that predict a series of states that visually generate the outcome the user anticipates based on the user's interaction with the virtual clothing.

Abstract: A system and method for rendering vector graphics using precomputed textures, includes receiving a vector image, the vector image including a plurality of instructions, each instruction for rendering at least a geometric primitive; detecting in the plurality of instructions an instruction for generating a first Bezier curve; selecting a first precomputed curve in a texture map to match the first Bezier curve; and generating a raster image based at least on the first precomputed curve. In an embodiment selecting the first precomputed curve includes computing a transformation matrix between the first precomputed curve and target coordinates, wherein the target coordinates are coordinates of a display; computing texture coordinates based on the computed transformation matrix and the texture map; and rendering an adapted precomputed curve, based on the texture map and the computed texture coordinates.

Abstract: The present disclosure discloses a method and apparatus for processing data, a computer device and computer-readable storage medium. The method comprises: acquiring image data of a human body; identifying a two-dimensional posture of the human body based on the image data; comparing the identified two-dimensional posture to a posture database to determine preset parts of the two-dimensional posture; and assigning cloth physical property of to-be-tried-on apparel to a part of the preset parts of the two-dimensional posture covered by original apparel. The present disclosure can greatly improve the efficiency of data processing, thereby improving user experiences.

Abstract: A technique for performing a ray tracing operation for a ray is provided. The method includes performing one or more ray-box intersection tests for the ray against one or more bounding boxes of a bounding volume hierarchy to eliminate one or more nodes of the bounding volume hierarchy from consideration, for one or more triangles of the bounding volume hierarchy that are not eliminated by the one or more ray-box intersection tests, performing one or more ray-triangle intersection tests utilizing samples displaced from a centroid position of the ray, and invoking one or more shaders of a ray tracing pipeline for the samples based on results of the ray-triangle intersection tests.

Abstract: Image information and identification information identifying an external device are acquired from the external device. An image based on the image information is displayed on a display surface. A drawing object is generated from a trajectory of a pointing unit in a drawing area on the display surface based on the image as a reference. The drawing object is stored in association with the identification information into a memory. The drawing object associated with the identification information in the memory is displayed on the display surface, as linked to the image.

Abstract: Generating a look of characters using visible brush strokes, including: receiving an input image and a pattern image; replacing each patch in the pattern image with an average color of pixels in the input image corresponding to pixels of each patch to produce a color-averaged output; and applying distortion to the color-averaged output using a distortion image.

Abstract: Mobile devices, such as a smartphone, tablet or wearable, are leveraged to facilitate remote support between a user of the device, and a remote technician. In this approach, the mobile device is used as a tool on behalf of the remote technician. In particular, and in one embodiment, the mobile device is used to transfer images to the remote technician's desktop. The remote technician desktop is provisioned with a whiteboard functionality by which the remote technical draws on the camera image that the remote technician is then viewing. The resulting annotation(s) are then transferred back over the network and drawn on the end user's camera view. In this manner, the technician highlights any area of the camera image, and those highlights are visible on the end user mobile device regardless of whether the local end user rotates the view or moves the mobile device camera during the support session.

Abstract: Object annotation is images is tedious time consuming task when large volume of data needs to annotated. Existing methods limit to semiautomatic approaches for annotation. The embodiments herein provide a method and system for a deep network based architecture for automatic object annotation. The deep network utilized is a two stage network with first stage as an annotation model comprising a Faster Region-based Fully Convolutional Networks (F-RCNN) and Region-based Fully Convolutional Networks (RFCN) providing for two class classification to generate annotated images from a set of single object test images. Further, the newly annotated test object images are then used to synthetically generate cluttered images and their corresponding annotations, which are used to train the second stage of the deep network comprising the multi-class object detection/classification model designed using the F-RCNN and the RFCN as base networks to automatically annotate input test image in real time.

Abstract: An electronic apparatus and a method of controlling the electronic apparatus are provided. The electronic apparatus includes a display configured to display an image, and a controller electrically connected to the display. The controller is configured to control the display to display a region of the image, using a first reproducing method, identify either one or both of a first event in which a control signal is externally received and a second event occurring based on a result of analyzing a feature of the region of the image, and change the first reproducing method to a second reproducing method, based on either one or both of the first event and the second event being identified.

Abstract: Apparatus and methods for the stitch zone calculation of a generated projection of a spherical image. In one embodiment, a computing device is disclosed which includes logic configured to: obtain a plurality of images; map the plurality of images onto a spherical image; re-orient the spherical image in accordance with a desired stitch line and a desired projection for the desired stitch line; and map the spherical image to the desired projection having the desired stitch line. In a variant, the desired stitch line is mapped onto an optimal stitch zone, the optimal stitch zone characterized as a set of points that defines a single line on the desired projection in which the set of points along the desired projection lie closest to the spherical image in a mean square sense.

Abstract: Provided are an apparatus and a method of inputting note information to an image of a shot object in order to display an image of a shot object in which the note information has been reflected.

Abstract: Apparatus and methods for the stitch zone calculation of a generated projection of a spherical image. In one embodiment, a computing device is disclosed which includes logic configured to: obtain a plurality of images; map the plurality of images onto a spherical image; re-orient the spherical image in accordance with a desired stitch line and a desired projection for the desired stitch line; and map the spherical image to the desired projection having the desired stitch line. In a variant, the desired stitch line is mapped onto an optimal stitch zone, the optimal stitch zone characterized as a set of points that defines a single line on the desired projection in which the set of points along the desired projection lie closest to the spherical image in a mean square sense.

Abstract: An image supply device used with an image display device and an operation detection device adapted to detect an indication location in accordance with a position indication operation on a display surface includes a drawing section adapted to generate a superimposition image to be displayed while being superimposed on an original image based on the indication location detected by the operation detection device, a first image generation section adapted to generate a first composite image by superimposing the superimposition image generated by the drawing section on the original image, a second image generation section for generating a second composite image by superimposing an operating image for instructing a process of the superimposition image generated by the drawing section on the first composite image in response to a change in the original image, and an output section adapted to output the second composite image to the image display device.

Abstract: A direct manipulation user interface provides a user with a means to interact with control points associated with smart objects to create and modify complex 3D graphic objects. The direct manipulation user interface includes a precision control mechanism that enables a user to specify precise measurements for a transformation through the user's interaction with a control point. The direct manipulation user interface also includes a history bar that enables a user to scroll back to a previous stage in the design process and to undo a sequence of transformations through the user's interaction with the history bar.

Abstract: A method of generating surface geometry information of an object within an imaged region using an imaging system comprising a camera and a source of structured light, the source of structured light comprising a source of a plurality of rays of light. The method comprising obtaining first image data comprising a plurality of pixels, the first image data comprising image data representing the object and first structured light incident on the object, the first structured light comprising a periodic pattern comprising a plurality of pattern elements and having a first spatial frequency projected from said source of structured light and obtaining second image data comprising a plurality of pixels, the second image data comprising image data representing the object and providing information associating each of the plurality of image pixels of the second image data with a ray of said source of structured light.

Abstract: A method of estimating a fragment count for the display of at least one three-dimensional (3D) object. The method comprises determining an ellipsoid representative of a set of vertices defined by coordinates of the at least one 3D object, applying a transformation to the ellipsoid, calculating a projection area of the transformed ellipsoid, and estimating the fragment count for the display of the 3D object based at least partly on the calculated projection area of the transformed ellipsoid.

Abstract: Systems and methods are described for identifying the video content as spherical video or non-spherical video in response to determining that frame scores and video scores satisfy a threshold level. For example, a plurality of image frames can be extracted from video content, classified in a dual stage process, and scored according to particular classification and scoring mechanisms.

Abstract: This invention has an object to provide an image editing program and apparatus allowing users to intuitively produce images covering the omnidirection. In a virtual space, an omnidirectional image is projected according to a coordinate conversion and displayed at a display device 20. For omnidirectional image edition, a view direction and a view angle are changed in the virtual space with a pointing device 30, and under control of a central control unit 11, display of the omnidirectional image in a screen image is renewed to perform two-dimensional drawing to an image for drawing having the same coordinate system as that of the screen image with the pointing device 30 using the screen image as a clue. After the end of drawing, the coordinate conversion is made to the drawing image to project the image at a proper position of the omnidirectional image. The omnidirectional image is thus completed by repeating the steps of view direction changes and drawing.

Abstract: An image capture device, a depth generating device and a method thereof are disclosed. The present disclosure is characterized in that a depth calculation technology with a structure light projection and a pictorial depth calculation technology are combined to better both of resolution and accuracy of the calculated image depth. In addition, the utilization of a modified flashlight enables the combination of the two technologies to be applied to a hand-held capture device.

Abstract: Water surface and other effects are efficiently simulated to provide real time or near real time imaging on low-capacity computer graphics computation platforms. Water and other surfaces are modeled using multiple independent layers can be dynamically adjusted in response to real time events. The number of layers used in a given area can be adjusted to reduce computational loading as needed. Different algorithms can be employed on different layers to give different effects. The multiple layer modeling is preferably converted to polygons using an adaptive polygon mesh generator based on camera location and direction in the 3D world to provide automatic level of detailing and generating a minimal number of polygons. The visual effects of water droplets and other coatings on see-through surfaces can be modeled and provided using indirect texturing.

Abstract: An autonomous vehicle configured to detect and avoid pedestrians may use information from LIDAR or other range-based sensors. An example method involves: (a) receiving, at a computing device, range data corresponding to a plurality of objects in an environment of a vehicle, wherein the range data comprises a plurality of first data points; (b) generating a spherical data set comprising a plurality of second data points, wherein spherical coordinates for each second data point are generated based on a corresponding one of the first plurality of data points; and (c) determining a two-dimensional map based on the spherical data set comprising the plurality of second data points, wherein the two-dimensional map comprises a plurality of pixels, wherein each pixel of the plurality of pixels is indicative of a plurality of parameters corresponding to the plurality of objects in the environment.

Abstract: A method of misalignment correction in a structured light device is provided that includes extracting features from a first captured image of a scene, wherein the first captured image is captured by an imaging sensor component of the structured light device, and wherein the first captured image includes a pattern projected into the scene by a projector component of the structured light device, matching the features of the first captured image to predetermined features of a pattern image corresponding to the projected pattern to generate a dataset of matching features, determining values of alignment correction parameters of an image alignment transformation model using the dataset of matching features, and applying the image alignment transformation model to a second captured image using the determined alignment correction parameter values.

Abstract: An image processing apparatus configured to perform an appropriate blurring processing in which a height difference in the surface shape with fine unevenness is taken into consideration, and to reproduce the surface shape faithfully corresponding to an original image. The image processing apparatus for generating computer graphics expressing an object includes a first acquisition unit configured to acquire height information representing a relative height difference in a surface of the object, a second acquisition unit configured to acquire at least one scattering function representing an internal scattering characteristic of light in the object, and a calculation unit configured to calculate a luminance value of the object based on the height information and the scattering function.

Abstract: Surfaces without a global surface coordinate system are divided into surface regions having local surface coordinate systems to enable the caching of surface attribute values. A surface attribute value for a surface region may include contributions from two or more adjacent surfaces. Sample points may be arranged at the corners, rather than centers, of surface regions and include prefiltered values based on two or more surfaces. A renderer may sample the surface attribute function using these prefiltered values without accessing any adjacent surfaces, even if the renderer's filter crosses a surface boundary. A multiresolution cache stores surface attribute values at different resolution levels for surface regions of one or more surfaces, which may be discontiguous. Two or more resolution levels may have the same number of sample points but have values based on filters with different areas and spatial frequency limits. Resolution levels may be selected based on geodesic distance on a surface.

Abstract: A wave modeler usable with a rendering engine and for generating surface models usable for rendering images of scenes having surfaces therein reads user inputs including a desired displacement value, determines a vertical displacement wave representing displacements along a wave, determines a plurality of sample points each having an ordinal position on the vertical displacement wave, determines a horizontal displacement wave, maps the horizontal displacement wave to the plurality of sample points, adjusts horizontal displacement of one or more of the plurality of sample points to prevent, avoid or reduce intersection of the wave with itself, and generates a representation of the wave that is storable as a geometric model usable by a rendering image to generate an image with corresponding displacements of the wave.

Abstract: A system, method and apparatus are disclosed, in which a processing unit is configured to perform secondary processing on graphics pipeline data outside the graphics pipeline, with the output from the secondary processing being integrated into the graphics pipeline so that it is made available to the graphics pipeline. A determination is made whether to use secondary processing, and in a case that secondary processing is to be used, a command stream, which can comprise one or more commands, is provided to the secondary processing unit, so that the unit can locate and operate on buffered graphics pipeline data. Secondary processing is managed and monitored so as to synchronize data access by the secondary processing unit with the graphics pipeline processing modules.

Abstract: An image rendering device realizes stereoscopic viewing of a joint background image. A DIBR unit 17 applies pixel shifting to each background image constructing the joint background image and also conducts boundary processing relative to the pixel shifting. The joint background image is composed of one or more background images stitched together along their edges on a three-dimensional model. The pixel shifting is to shift pixels of each background image in the row direction. The amount of shift applied to each pixel is determined based on the depth value of a corresponding pixel of a depth image. The boundary processing is to extract pixels shifted out of the display region of a given background image as a result of pixel shifting and add the extracted pixels to an edge of another background image adjacent to the given background image in the row direction.

Abstract: A method for projecting geographic data (e.g., latitude and longitude coordinates) from a spherical surface onto a two-dimensional Cartesian space is provided. Such a capability can employ a coordinate testing and transformation method to map the projected geographic data within the two-dimensional Cartesian space so that distances measured on the spherical surface remain relatively consistent with distances measured in the two-dimensional Cartesian space. Further, this capability allows for the use of efficient search algorithms to find projected geographic points within a particular geographic search area.

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: A projection display apparatus includes an imager that modulates light emitted from a light source and a projection unit that projects light emitted from the imager on a projection surface. The projection display apparatus includes: an imager controller that controls the imager to display a test pattern image in which a characteristic point is defined by at least three adjacent regions; an acquisition unit that acquires a captured image of the test pattern image from an imaging element configured to capture the test pattern image projected on the projection surface; and an adjustment unit that identifies the characteristic point included in the captured image on the basis of the captured image acquired by the acquisition unit and adjusts an image to be projected on the projection surface on the basis of the identified characteristic point. The at least three adjacent regions surround the characteristic point and are adjacent to the characteristic point.

Abstract: A product modeling system and method are provided. On one embodiment, the product modeling system is used to model a piece of apparel, such as a shirt, with a design wherein the model with the design is used to display the piece of apparel with the design to a consumer.

Abstract: A method for curved planar reformation of an image includes receiving a data volume including a medial axis tree of a vessel tree, determining a global rotation axis of the medial axis tree, and casting a line segment from a vessel tree root of the medial axis tree into a predefined direction perpendicular to the global rotation axis. The method includes projecting the medial axis tree onto a reference plane along the line segment. The method further includes re-sampling, from at least one medial axis point of a reference plane, the data volume using a vector perpendicular to a medial axis tangent of the reference plane, wherein the vector defines a sampling direction. The method includes rendering an image of the vessel tree along the vector.

Abstract: A method and system for creating and using a virtual dressing room, by superimposing a non-linearly stretchable object image onto a base image in a display screen of a communication device, the images being planar. The method comprises scanning an encoded indicium associated with the object image, accessing and uploading a URL associated with the object image, the object image including a plurality of object image critical points, accessing the base image at the communication device, the base image including a plurality of base image critical points respectively corresponding to the object image critical points, re-mapping the object image via global transformation of coordinates associated with the object image critical points, such that the re-mapped object image critical points coincide with the respective base image critical points, and superimposing the re-mapped object image onto the base image for display at the display screen.

Abstract: An image processing apparatus includes a combining processing unit combining plural images into a piece of combined image. The plural images is taken by a plurality of image-capturing from a certain position to different plural directions. The combining processing unit configured to extract a parameter by performing block matching processes at individual boundaries in such a manner that boundaries a plurality of selected images are disposed in overlapping relation, perform block matching processes of all boundaries to be combined based on the parameter, evaluate results of the block matching processes with respect to all the boundaries, and perform combining the images to reduce errors by updating an optical axis direction so as to reduce errors in all the boundaries.

Abstract: Rendering a deforming object in animation including: defining a deforming object surface angle; identifying a normal vector discontinuity point using the deforming object surface angle; defining front part and back part of the deforming object with reference to the normal vector discontinuity point; dividing the front part of the deforming object into zones based on the deforming object surface angle; dividing the back part of the deforming object into zones based on the deforming object surface angle; and rendering each zone.

Abstract: Systems and associated methods for processing textures in a graphical processing unit (GPU) are disclosed. Textures may be managed on a per region (e.g., tile) basis, which allows efficient use of texture memory. Moreover, very large textures may be used. Techniques provide for both texture streaming, as well as sparse textures. A GPU texture unit may be used to intelligently clamp LOD based on a shader specified value. The texture unit may provide feedback to the shader to allow the shader to react conditionally based on whether clamping was used, etc. Per region (e.g., per-tile) independent mipmap stacks may be used to allow very large textures.

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: A product modeling system and method are provided. On one embodiment, the product modeling system is used to model a piece of apparel, such as a shirt, with a design wherein the model with the design is used to display the piece of apparel with the design to a consumer.

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: A curved surface rendering method grids a curved surface to a plurality of triangles, and further divides the plurality of triangles to sub-triangles. Furthermore, the method determines surface triangles and inner triangles from all triangles of the curved surface, and displays the surface triangles on a display device.

Abstract: A biometrics system captures and processes a handprint image using a structured light illumination to create a 2D representation equivalent of a rolled inked handprint. A processing unit calculates 3D coordinates of the hand from the plurality of images and maps the 3D coordinates to a 2D flat surface to create a 2D representation equivalent of a rolled inked handprint.

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: An image display system for displaying a planar image on a curved viewing surface, such as a theater dome, with minimized image distortion. In order to display the image, a virtual surface, which is a representation of the curved viewing surface, is textured with the image using an angular distribution to thereby form a textured virtual image. The textured virtual image is then displayed onto the curved viewing surface.

Abstract: A method for filling closed regions in a drawing using a region filling tool. Rather than selecting individual regions to fill, or filling based on style-by-layer techniques, the user creates a path or an area boundary to identify the regions to be filled. A graphics application may then fill each region that intersects the path or area boundary with a selected color or graphical style. In this manner, multiple regions in the drawing may be identified using one interaction with the region filling tool, allowing the user to more efficiently and intuitively fill regions in the drawing with the selected color or graphical style.

Abstract: A method for obtaining and analyzing information objects including generating, collecting or discovering information objects. The information objects are signified at least in part using deliberately ambiguated signifier prompts, for example, linear scale opposing negatives or positives, and/or multi-dimensional signifier prompts. The information objects may comprise text or non-text fragments, and may be generated or selected. The responses to the signifier prompts are stored with the fragments to provide a dataset of signified fragments. The signified fragments may be analyzed based on the signifiers and can be utilized as part of an explorable knowledge repository, or objective measures can be created to aid in mass opinion capture or human attitude auditing. The fragments may be represented on a graphical template.