Abstract: A hierarchical acceleration structure is generated for intersection testing in a ray tracing system. Nodes of the hierarchical acceleration structure are determined, wherein each of the nodes represents a region in a scene, and wherein the nodes are linked to form the hierarchical acceleration structure. Data is stored representing the hierarchical acceleration structure. The stored data defines the regions represented by a plurality of the nodes of the hierarchical acceleration structure. At least one node is an implicitly represented node, wherein data defining a region represented by an implicitly represented node is not explicitly included as part of the stored data but can be inferred from the stored data.

Abstract: Three dimension (3D) model generation systems and methods are operable to generate 3D model data corresponding to images of a physical object of interest that are viewed in a presenting media content event. An exemplary embodiment receives a user request that is associated with an interest by the user to obtain a 3D model of a physical object of interest that is being shown in a scene of a currently presenting media content event. A plurality of video image frames are selected from the scene. Then, 3D model data of the physical object of interest is generated based on at least the selected video image frames of the scene.

Abstract: Technology described herein can be embodied in a method of providing visual feedback during surgery. The method includes obtaining a set of vectors representing a model of an anatomical organ, the set produced from a representation of the organ as imaged under one or more imaging modalities. The method includes obtaining a set of pixel positions of a display device, wherein the pixel positions correspond to a view of the organ. The method further includes generating, using at least a portion of the set of vectors, multiple fragment-vectors for each pixel position in the set of pixel positions, the multiple fragment-vectors each representing a corresponding portion of the organ along a line-of-sight through the organ, and generating a pixel value for each pixel position in the set of pixel positions, and presenting, on the display device, an augmented image of the view of the organ using the generated pixel values.

Abstract: The present disclosure is directed to a software tool that facilitates the presentation of a three-dimensional view of a construction project as well as the generation of various types of two-dimensional technical drawings based on this three-dimensional view. In one implementation, the software tool causes a computing device to engage in the following operations. The computing device may receive an indication of a desired clip height of a three-dimensional view at which to generate a two-dimensional technical drawing; identify a subset of meshes that intersect with a two-dimensional plane at the desired clip height; determine respective portions of each mesh that intersect the two-dimensional plane at the desired clip height; compile a dataset that defines the two-dimensional drawing; and render the two-dimensional drawing using the compiled dataset.

Abstract: A mediated-reality system for surgical applications incorporates pre-operative images and real-time captured images of a surgical site into a visualization presented on a head-mounted display worn by a surgeon during a surgical procedure. The mediated-reality system tracks the surgeon's head position and generates real-time images of the surgical site from a virtual camera perspective corresponding to the surgeon's head position to mimic the natural viewpoint of the surgeon. The mediated-reality system furthermore aligns the pre-operative images with the real-time images from the virtual camera perspective and presents a mediated-reality visualization of the surgical site with the aligned pre-operative three-dimensional images or a selected portion thereof overlaid on the real-time images representing the virtual camera perspective.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design of physical structures include, in one aspect, a method for increasing smoothness between a set of adjoining surface patches includes: identifying surface patches corresponding to a portion of a modeled surface to be smoothed, where the surface patches are defined by control vertices from a control mesh; smoothing the portion of the modeled surface based on continuity, where the smoothing includes determining a continuity measure at an interface between each pair of adjoining surface patches, and modifying positions of a subset of the control vertices, thereby modifying the surface patches, by targeting an overall improvement in the continuity measures for the interfaces, while also targeting an overall minimum of modification of positions of the control vertices; and processing the modified positions of the subset of the control vertices within the modelled surface for output.

Abstract: A computer implemented method or system including a map conversion toolkit and a map Population toolkit. The map conversion toolkit allows one to quickly trace the layout of a floor plan, generating a file (e.g., GeoJSON file) that can be rendered in two dimensions (2D) or three dimensions (3D) using web tools such as Mapbox. The map population toolkit takes the scan (e.g., 3D scan) of a room in the building (taken from an RGB-D camera), and, through a semi- automatic process, generates individual objects, which are correctly dimensioned and positioned in the (e.g., GeoJSON) representation of the building. In another example, a computer implemented method for diagraming a space comprises obtaining a layout of the space; and annotating or decorating the layout with meaningful labels that are translatable to glanceable visual signals or audio signals.

Abstract: A system comprises an encoder configured to compress attribute information and/or spatial for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. To compress the attribute and/or spatial information, the encoder is configured to convert a point cloud into an image based representation. Also, the decoder is configured to generate a decompressed point cloud based on an image based representation of a point cloud. A block/sub-block organization scheme is used to encode blocks and sub-blocks of an occupancy map used in compressing the point cloud. Binary values are assigned to blocks/sub-blocks based on whether they contain patches projected on the point cloud. A traversal path is chosen that takes advantage of run-length encoding strategies to reduce a size of an encoded occupancy map. Also, auxiliary information is used to further improve occupancy map compression.

Abstract: Embodiments of the present disclosure relate to systems and methods for generating 3D models of floor plans using two-dimensional (2D) image inputs. According to an embodiment, a three-dimensional building model generation system is disclosed that can include a two-dimensional image receive module to receive a 2D image pertaining to the floor plan, an image processing module to processes the two-dimensional image to generate a binary image, a two-dimensional floor plan graph generation module to extract two-dimensional geometry from the binary image to generate a two-dimensional floor plan graph, and a three-dimensional model generation module to generate a 3D model of the floor plan by performing geometric extrusion of the two-dimensional floor plan graph based on one or more cyclic wall graphs and one or more connectives.

Abstract: The present invention relates to a computer implemented method for modifying a digital three-dimensional model (3) of a dentition comprising: displaying an image of the dentition by applying a virtual camera to the three-dimensional model to render the image for a display (1); acquiring a line drawn by a user on the image on the display (1); projecting the acquired line, using the virtual camera (4), to a three-dimensional projection surface (7) approximating the shape of the dental arches and extending the upper and lower dental arches to cover any opening therebetween; obtaining visible teeth arch contour curves, namely incisal curve and gingiva border curve, of the upper and lower teeth arches, and projecting the teeth arch contour curves to the projection surface; selecting one of the teeth arch contour curves as teeth arch contour curve to be modified and selecting the other teeth arch contour curve of the same teeth arch or a curve derived therefrom as a baseline curve; deforming all teeth belonging

Abstract: Based on a three-dimensional map in which three-dimensional information of a scene captured by an image capturing apparatus and a position and orientation of the apparatus are associated with each other and an image captured by the apparatus, a first position and orientation of the apparatus at the time of capturing the image is derived. The map is updated based on the captured image and the first position and orientation. A relative position and orientation between the first position and orientation and a second position and orientation of the apparatus derived by a method different from a method of deriving the first position and orientation or at a point of time different from a point of time of deriving the first position and orientation is derived. The map is corrected based on the relative position and orientation.

Abstract: A method for generating an electro-anatomical map to represent an underlying metric associated with heart tissue it is provided. The method comprises receiving, by a mapping system, point cloud data collected for the underlying metric at various locations within the heart; generating, by the mapping system, a surface mesh to represent the geometry of a heart, said surface mesh comprising a plurality of mesh points arranged as a series of interconnected triangles, wherein each mesh point lies on the surface of the heart, and is generated based on the point cloud data; rendering the surface mesh in a viewer application, comprising coloring the mesh points in the surface mesh based on values of the underlying metric associated with each of the mesh points and a color scale; and allowing a user to dynamically adjust the color scale based on a histogram.

Abstract: Provided are systems and methods for single image-based body animation. An example method includes receiving an input image that includes a body of a person and segmenting the input image into a body portion and a background portion. The method further includes fitting a model to the body portion. The model is configured to receive a set of pose parameters representing a pose of the body and generate an output image including an image of the body adopting the pose. The method further includes receiving a series of further sets of pose parameters, each representing at least one of further poses of the body. The further sets of pose parameters are generated using a generic model. The method also includes generating a series of output images of the body adopting the further poses and generating an output video based on the series of output images.

Abstract: The present disclosure relates generally to for displaying a set of images based on captured image data. In some embodiments, a system displays a first set of images corresponding to a first perspective in a virtual reality (VR) (or mixed reality (MR)) environment. The system receives a request while displaying the first set of images. The system captures image data corresponding to a second perspective in the VR (or MR) environment in response to receiving the request. The system displays a second set of images based on the captured image data.

Abstract: Systems and methods for generating cartoon images or emojis of an individual from a photograph of the individual is described. The systems and methods involve transmitting a picture of the individual, such as one taken with a mobile device, to a server that generates a set of emojis showing different emotions of the individual from the picture. The emojis are then transmitted to the mobile device and are available for use by the user in messaging applications, emails, or other electronic communications. The emojis can be added to the default keyboard of the mobile device or be generated in a separate emoji keyboard and be available for selection by the user.

Abstract: Examples disclosed herein may involve (i) obtaining 2D image data and 3D sensor data that is representative of an area, (ii) identifying a first set of pixels associated with ephemeral objects detected in the area and a second set of pixels associated with non-ephemeral objects detected in the area, (iii) identifying a first set of ephemeral 3D data points associated with the detected ephemeral objects and a second set of non-ephemeral 3D data points associated with the detected non-ephemeral objects, (iv) mapping the first and second sets of 3D data points to a grid of voxels associated with the area, (v) making a determination that one or more voxels in the grid each contain a threshold extent of ephemeral data points, and (vi) based at least in part on the determination, filtering the 3D sensor data to remove the 3D data points contained within the one or more voxels.

Abstract: An information processing apparatus includes a processor. The processor is configured to set in three-dimensional space in which plural users are present, an intersection area that is an area in which fields of view of the plural users intersect as a shared area that is an area to be shared by the plural users.

Abstract: A product image representing an upper body of a vehicle having a reference shape and a shift index segment image linearly extending from each of a plurality of designated virtual space locations of the product image in each of a plurality of directions of virtual spaces are displayed. Each of the plurality of designated virtual space locations corresponds to each of a plurality of designated real space locations of the upper body of the vehicle having the reference shape. A length of the shift index segment image represents a quantity of a virtual space position shift amount. The “virtual space position shift amount” corresponds to a real space position shift amount in a direction of a real space at a designated real space location of the upper body based on reference data of the upper body.

Abstract: A method for generating and updating a three-dimensional representation of a surgical site based on imaging data from an imaging system is disclosed. The method comprises the steps of generating a first image of the surgical site based on structured electromagnetic radiation emitted from the imaging system, receiving a second image of the surgical site, aligning the first image and the second image, generating a three-dimensional representation of the surgical site based on the first image and the second image as aligned, displaying the three-dimensional representation on a display screen, receiving a user selection to manipulate the three-dimensional representation, and updating the three-dimensional representation as displayed on the display screen from a first state to a second state according to the received user selection.

Abstract: There is provided an image processing apparatus and an image processing method capable of transmitting data of a 3D model in object units. The image processing apparatus includes a 3D model selection unit that selects an object that satisfies a predetermined condition from among objects of a plurality of 3D models and a transmitter that transmits 3D model data of the selected object. The present technology is applied to, for example, an apparatus and the like for transmitting 3D model data of a 3D model via a network.