Abstract: A holographic calling system can capture and encode holographic data at a sender-side of a holographic calling pipeline and decode and present the holographic data as a 3D representation of a sender at a receiver-side of the holographic calling pipeline. The holographic calling pipeline can include stages to capture audio, color images, and depth images; densify the depth images to have a depth value for each pixel while generating parts masks and a body model; use the masks to segment the images into parts needed for hologram generation; convert depth images into a 3D mesh; paint the 3D mesh with color data; perform torso disocclusion; perform face reconstruction; and perform audio synchronization. In various implementations, different of these stages can be performed sender-side or receiver side. The holographic calling pipeline also includes sender-side compression, transmission over a communication channel, and receiver-side decompression and hologram output.

Abstract: Systems and methods for presenting a map and changing a direction of an object on screen. In an aspect, an elongated map segment is presented according to a device pointing direction. In another aspect, location-based information is sorted and presented according to a device pointing direction. In other aspects, a direction in which an object faces is changed according to a device pointing direction, and a direction of motion of an object is changed according to a device pointing direction.

Abstract: 3D reconstruction method based on deep learning includes the following steps: (1) The potential vector constrained in the input image is used to reconstruct the complete 3D shape of the target, and the mapping between the part and the complete 3D shape is learned, then the 3D reconstruction of a single depth image is realized. (2) Learn the intermediate feature representation between the 3D real object and the reconstructed object to obtain the target potential variables in step (1). (3) The voxel floating value predicted in step (1) is transformed into binary value by using the limit learning machine to complete high-precision reconstruction.

Abstract: A method of playing back an image in a display device obtains a stereo image corresponding to both eyes of a user including a left eye and a right eye, obtains positions of the eyes determines warping transform information corresponding to the positions of the eyes based on a database (DB) provided in advance based on a curvature of an display plane of the display device, warps the stereo image by applying the warping transform information to the stereo image, determines pixel values of a display panel included in the display device from the warped stereo image by performing light field rendering based on the positions of the eyes, and reproduces the determined pixel values on the display panel.

Abstract: In an approach to image compression while retaining feature information at original coordinates, one or more computer processors compress an image while retaining pattern and feature information at original coordinates, wherein the image is a full resolution 3D image. The one or more computer processors create one or more image subsets based on the one or more determined regions of interest identified by utilizing a first pass selection of the regions of interest based on the compressed image. The one or more computer processors train one or more models based the created one or more image subsets that contain one or more regions of interest based on the compressed image.

Abstract: Based on information regarding positions of two-dimensional images included in a first three-dimensional image and two-dimensional images included in a second three-dimensional image, an information processing apparatus acquires information regarding a first range, which is a range of positions where the two-dimensional images included in the first three-dimensional image are present, and a second range, which is a range of positions where the two-dimensional images included in the second three-dimensional image are present, and displays, on a display unit, a figure indicating the first range such that an area, in the first range, included in the second range is distinguishable.

Abstract: In order to improve manufacturing convenience and precision, the present invention provides a digital denture manufacturing method comprising: a first step of acquiring a three-dimensional work image, on which occlusion information between a target dental arch and an opposing dental arch and implant information of a fixture implanted in the target dental arch are displayed, and preparing a temporary denture in which a binding region formed to correspond to a binding portion profile of an abutment fastened to the fixture is arrayed and arranged; a second step of acquiring an auxiliary scan image for the temporary denture; a third step of acquiring, from the auxiliary scan image, a correction surface image on three-dimensional surface information of an inner surface-side engagement groove of the temporary denture including the binding region; and a fourth step of designing and manufacturing a digital denture having a virtual binding groove corresponding to the position and the shape of the three-dimensional sur

Abstract: A method for preemptively generating and rendering a view of a computerized image is provided. The method may include determining rendering parameters for the computerized image by predicting an action to be performed on the computerized image, wherein the action modifies a view of the computerized image, and wherein the determined rendering parameters are based on the modified view of the computerized image. The method may further include preemptively rendering the view of the computerized image that is based on the determined rendering parameters before the action is performed on the computerized image.

Abstract: Some embodiments of the invention provide a method for concurrently presenting two synchronized animations based on an input value that is received through an input interface of a device. The method defines, based on the received input, a first animation that presents a first animated object, and then uses a set of attributes of the first animation to define a second animation that presents a second animated object. The method then displays at least portions of the first and second animations concurrently. In some embodiments, the method displays the first and second animations on a display screen of the device, or on a display screen connected to the device.

Abstract: The disclosure presents a technique for utilizing ray tracing to produce high quality visual scenes with shadows while minimizing computing costs. The disclosed technique can lower the number of rays needed for shadow region rendering and still maintain a targeted visual quality for the scene. In one example, a method for denoising a ray traced scene is disclosed that includes: (1) applying a pixel mask to a data structure of data from the scene, wherein the applying uses the scene at full resolution and pixels at the edge of a depth boundary change are identified using the pixel mask, (2) generating a penumbra mask using the data structure, (3) adjusting HitT values in the packed data buffer utilizing the penumbra mask, and (4) denoising the scene by reducing scene noise in the data of the data structure with adjusted HitT values.

Abstract: Dynamic spread anti-aliasing is described. In some embodiments, a filled object is segmented into control tiles. Along the object border, multiple exterior control tiles respectively correspond to multiple curves forming the border. For each curve, one side is filled and the other is anti-aliased to smooth the appearance of the filled object. Each exterior control tile is expanded to create an expanded control tile having a spread zone that includes additional pixels. For example, a control triangle is transformed into a control rectangle, and the control rectangle is enlarged to create an expanded control rectangle by extending an edge outward and away from the curve on the side to be anti-aliased. The additional pixels of the spread zone are subjected to anti-aliasing, such as by applying alpha modulation to the pixels based on respective distances between the pixels and the curve. For subpixel zoom levels, pixel color can be adjusted.

Abstract: This disclosure generally relates to character animation. More specifically, this disclosure relates to pose selection using data analytics techniques applied to training data, and generating 2D animations of illustrated characters using performance data and the selected poses. An example process or system includes extracting sets of joint positions from a training video including the subject, grouping the plurality of frames into frame groups using the sets of joint positions for each frame, identifying a representative frame for each frame group using the frame groups, clustering the frame groups into clusters using the representative frames, outputting a visualization of the clusters at a user interface, and receiving a selection of a cluster for animation of the subject.

Abstract: The present disclosure describes a system and method for a marker-based augmented reality system. The method includes acquiring image data from a camera, analyzing the image data to identify at least one marker, the at least one marker being associated with a physical location in a real-world environment, determining information represented via the at least one marker, the information represented via the at least one marker including at least one of content data, metadata, or server data, generating content based on the at least one of the content data, the metadata, or the server data, and presenting, via a display, the content overlaying a displayed representation of the real-world environment, the content being presented at one or more locations in the displayed representation of the real-world environment relative to the physical location associated with the at least one marker.

Abstract: Methods and apparatus for an image generated for display by a head mountable display device include: defining a 2×2 pixel mask pattern for a region of the image, indicating the location of one or more pixels and corresponding masked pixels within the 2×2 pixel mask pattern; adapting a multi-sample anti-aliasing (MSAA) scheme to sample at one quarter resolution on a regular grid; sampling values using the adapted MSAA scheme to render the one or more respective pixels indicated by the 2×2 pixel mask, so as to generate a region of the image comprising one or more rendered pixels and corresponding missing pixels; and dilating one or more of the respective pixels to fill in the one or more missing pixels within the region of the image.

Abstract: A technique and computing device to render graphic objects associated with pattern paint in a digital medium environment are disclosed. The computing device comprises a graphics processing unit. The graphics processing unit associates a first surface to a framebuffer of the computing device, renders pattern cells at the first surface, and associates a second surface to the framebuffer of the computing device. The pattern cells correspond to pattern paints, and the pattern cells are rendered at the first surface independent of the sequential order of the pattern cells for rendering pattern paint. The graphics processing unit renders graphic objects associated with the pattern paints, and the graphic objects are rendered at the second surface in sequential order for rendering pattern paint.

Abstract: Systems and methods for digital rendering items with designs incorporate therein are disclosed. According to certain aspects, an electronic device may support a design application that may modify a digital image using an identity texture and a texture map, resulting in the modified digital image taking the shape or form of a portion of a digital model of an item. The electronic device may generate a digital rendering of the item using the modified digital image and the digital model of the item, and may enable a user to review the digital rendering and/or place an order for a physical version of the item according to the digital rendering.

Abstract: An apparatus to facilitate encoding of point cloud data is disclosed. The apparatus includes one or more processors to receive point cloud data including a plurality of images and camera parameters, generate encoded point cloud data including a color texture image and a depth image having cropped regions for each of the plurality of images, and metadata to describe the camera parameters and a mapping of the cropped regions to a real coordinate space.

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for modifying voxel-based 3D representations using 3D digital brush tools and/or resolution filters. For example, the disclosed systems can utilize 3D digital brush tools (e.g., a digital blur brush tool, a digital smudge brush tool, and/or a digital melt brush tool) to identify and modify one or more voxels within a 3D representation using multiple buffers of visual properties. Additionally, the disclosed systems can modify one or more voxels within a 3D representation by rendering the one or more voxels at varying levels of detail using an octree (e.g., a mosaic filter tool). In particular, the disclosed systems can identify one or more voxels within an octree that are smaller than a target voxel size. Moreover, the disclosed systems can combine the identified one or more voxels within the octree to render the 3D representation at varying levels of detail.

Abstract: Disclosed are an image processing method and device, and a three-dimensional imaging system. The method comprises the following steps of: acquiring a two-dimensional image to be processed; aligning the two-dimensional image to be processed to a grid template; performing mapping processing on the two-dimensional image to be processed by using a grid mapping table to acquire a first image, wherein the grid mapping table is used for representing the mapping relationship of grid images; mirroring the first image to acquire a second image; and synthesizing the first image and the second image to acquire the superimposed image of the first image and the second image.

Abstract: Provided is a display method of displaying on a display unit 2, an image group in which a plurality of images arranged on a first virtual axis are rotated about each of second virtual axes intersecting the first virtual axis, and further rotated about the first virtual axis, and are arranged side by side in a first direction, in which a length of the image in the first direction or a length of the image in a second direction which intersects the first direction is set such that, when a ratio of the length of the image in the first direction to the length of the image in the second direction is within a predetermined range, a shorter length of the length of the image in the first direction and the length of the image in the second direction is set to be constant in the image group, and when the ratio of the length of the image in the first direction to the length of the image in the second direction is outside the predetermined range, a longer length of the length of the image in the first direction and the le