Abstract: Certain aspects and features of this disclosure relate to modeling shapes using SDF approximation. For example, a method involves partitioning a surface-bounding volume configured to contain the surface of a shape using a volumetric grid. The method also involves approximating, using a basis function, a value of a signed distance function (SDF) for samples taken inside, and on a boundary of, each surface-containing cell of the grid, and storing, based on the sign changes, coordinates for each of the cells. The method further involves constructing a surface-bounding volume hierarchy for the shape by assigning bounding volumes to each of the cells based on the coordinates. The method additionally involves determining an intersection of a ray with each surface-bounding volume in the surface-bounding volume hierarchy and rendering or storing a representation of the shape based on each intersection.

Abstract: Various implementations disclosed herein include devices, systems, and methods that presents playback of application content within a three-dimensional (3D) environment. An exemplary process presents a first set of views that includes application content provided by the application within a 3D environment. The first set of views are provided from a first set of viewpoints during execution of the application. The process records of the execution of the application based on recording program state information and changes to the application content that are determined based on user interactions, and presents a second set of views including a playback of the application content within the 3D environment based on the recording. The second set of views are provided from a second set of viewpoints that are different than the first set of viewpoints.

Abstract: Systems and methods for extracting 3D shapes from unstructured and unannotated datasets are described. Embodiments are configured to obtain a first image and a second image, where the first image depicts an object and the second image includes a corresponding object of a same object category as the object. Embodiments are further configured to generate, using an image encoder, image features for portions of the first image and for portions of the second image; identify a keypoint correspondence between a first keypoint in the first image and a second keypoint in the second image by clustering the image features corresponding to the portions of the first image and the portions of the second image; and generate, using an occupancy network, a 3D model of the object based on the keypoint correspondence.

Abstract: Techniques are described for determining a user's unique depth perception in viewing virtual objects in virtual reality (VR) to make the VR experience more accurate and immersive for the user. The user can align a virtual image the user sees with a real-world image behind the virtual image to provide input indicating the user's depth perception. Depth perception parameters can then be determined from that for subsequently rendering VR objects to that user.

Abstract: Methods and apparatuses for automating the retopologization of 3D meshes including the automated selection and adjustment of correspondence points are described. The automated selection of correspondence points may be performed to refine locations of correspondence points using a matching score that is computed based on surface normal similarity between surfaces corresponding with a candidate correspondence point on an input scan mesh and a point on a morphable model of 3D surfaces. The matching score may also take into account a distance between a candidate correspondence point on the input scan mesh and a corresponding point on the morphable model of 3D surfaces and similarities in surface features, such as similarities in surface curvature at the candidate correspondence point on the input scan mesh and the corresponding point on the morphable model of 3D surfaces.

Abstract: There is provided an apparatus comprising means for: receiving, from a device, at least one parameter associated with the device, wherein the at least one parameter is for an environment viewable by the device, and generating a depth map associated with the environment, wherein the depth map comprises a plurality of pixels. The apparatus comprising means for, for each a pixel of the depth map: determining a depth value for the pixel using: i) the at least one parameter, and ii) at least one geometry library comprising geometry information about the environment, and storing the determined depth value of the pixel in the depth map. The apparatus comprising means for providing, to the device via a network, information related to the depth map comprising the determined depth values.

Abstract: A method and system for compensating anti-dizziness predicted in advance are provided. The method for compensating anti-dizziness predicted in advance includes the following steps. A six-degrees-of-freedom information is obtained. Through using a machine learning model, an attitude prediction compensation information is obtained according to the six-degrees-of-freedom information. A path information is obtained. A path prediction compensation information is obtained according to the path information. A road information is obtained. A road prediction compensation information is obtained according to the road information. A display information is compensated according to the attitude prediction compensation information, the path prediction compensation information, or the road prediction compensation information.

Abstract: Techniques for generation of compressed representations for appearance of fiber-based digital assets are described that support computationally efficient and high fidelity rendering of digital assets that include fiber primitives under a variety of lighting conditions and view directions. A processing device, for instance, receives a digital asset that includes fiber primitives to be included in a three-dimensional digital scene. The processing device generates a compressed representation of the digital asset that maintains a geometry of the digital asset and includes a precomputed light transport. The processing device then inserts the compressed representation into the digital scene, such as at a location relative to one or more light sources. The processing device applies one or more lighting effects to the compressed representation based on the precomputed light transport and the location relative to the one or more light sources.

Abstract: The disclosure provides apparatuses, methods and computer programmes to model geometric distortion in an image captured using an anamorphic lens. The apparatus may comprise one or more processors and memory storing one or more image arrays. Each image array may store a distorted image or an undistorted image. A distorted image is representative of pixel values of an image of a scene in a three-dimensional object space captured in a two-dimensional image space on an image plane by an imaging system having an anamorphic lens. An undistorted image is representative of pixel values of a distortion-compensated image of the scene in the three-dimensional object space captured in a two-dimensional image space in which information at locations in image plane in the distorted image have been transformed to remove the geometrical distortion effects of the anamorphic lens.

Abstract: A three-dimensional point cloud data processing system includes: one or more cameras that image an object to acquire one or more items of brightness information; and a controller that calculates point cloud data of the object from the one or more items of brightness information. The controller calculates at least one bounding box (BB), which surrounds the object and is formed by combining one or more rectangles, from at least one of the one or more items of brightness information, and calculates the point cloud data based on the at least one BB and the one or more items of brightness information.

Abstract: Techniques for configuring hair for animation include obtaining a first representation of a set of hairs on a surface and a second representation of a subset of the hairs. At a vertex of the surface, an interpolated hair is generated by minimizing a difference between a shape of a first hair and the interpolated hair. An edit is received to modify the shape of the first hair. At the vertex, a modified interpolated hair is generated by minimizing the difference between the modified hair shape and the modified interpolated hair. The interpolated hair and the modified interpolated hair are projected onto a root of a second hair. Rotation parameters indicating a rotation and a scaling factor indicating a scale difference between the projected interpolated hair and the projected modified interpolated hair are computed. The rotation parameters and scaling factor are applied to the second hair to propagate the edit.

Abstract: Embodiments described herein relate to the autonomous animation of Gestures by the automatic application of animations to Input Text—or the automatic application of animation Mark-up wherein the Mark-up triggers nonverbal communication expressions or Gestures. In order for an Embodied Agent's movements to come across as natural and human-like as possible, a Text-To-Gesture Algorithm (TTG Algorithm) analyses Input Text of a Communicative Utterance before it is uttered by a Embodied Agent, and marks it up with appropriate and meaningful Gestures given the meaning, context, and emotional content of Input Text and the gesturing style or personality of the Embodied Agent.

Abstract: Example systems, articles and methods to improve subjective quality of 3D reconstruction are disclosed. An example method disclosed herein includes obtaining image data of decoded video frame sequences of a same scene from multiple perspectives. The example method also includes generating a three dimensional (3D) structure of 3D points based on the image data. The example method further includes refining locations of the 3D points in the 3D structure based on a decoder-based bundle adjustment, the decoder-based bundle adjustment to refine the locations based on decoder prediction data.

Abstract: Embodiments of this application provide an image processing method, an electronic device, and a storage medium, which relates to the field of computer technologies. The method includes: receiving a first binding instruction delivered by an application program, where an operation type in the first binding instruction is not a read-only type, and a first framebuffer identifier in the first binding instruction indicates a first framebuffer used for on-screen rendering; receiving a first rendering instruction delivered by the application program, where the first rendering instruction indicates to draw first image content; and executing a second rendering instruction, to draw second image content on the first framebuffer, where the second rendering instruction indicates to draw the second image content, the second image content is generated based on the first image content, and a resolution of the second image content is higher than a resolution of the first image content.

Abstract: A computer-implemented method is disclosed. The method includes: determining a first position of a real display device in a real-world environment; receiving a request to display virtual information at a second relative position with respect to the first position in an AR version of the real-world environment; responsive to receiving the request: determining a displayable area associated with the second relative position; and causing the virtual information to be overlaid on the displayable area in the AR version of the real-world environment.

Abstract: Generation of three-dimensional (3D) object models may be challenging for users without a sufficient skill set for content creation and may also be resource intensive. One or more style transfer networks may be combined with a generative network to generate objects based on parameters associated with a textual input. An input including a 3D mesh and texture may be provided to a trained system along with a textual input that includes parameters for object generation. Features of the input object may be identified and then tuned in accordance with the textual input to generate a modified 3D object that includes a new texture along with one or more geometric adjustments.

Abstract: In implementation of techniques for vectorizing by piecewise deconstruction of object strokes, a computing device implements an image processing system to receive an input to initiate the generation of a boundary of an object in a digital image, such as a raster image. The image processing system detects a set of visually separated but semantically related strokes that represent the object's boundary. Based on the set of visually separated but semantically related strokes, the image processing system forms a combined stroke and generates the boundary of the object as a path based on the combined stroke. The resulting path mimics the visual appearance of the object in the digital image in a vector space.

Abstract: The present invention relates to a method and apparatus for filling a blank area of MPI view plane based on a pixel ray path. A method for generating multi plane image (MPI) data according to an embodiment of the present disclosure may comprise: calculating a pixel value according to each view for each photographed object, based on a plurality of input images photographed from a plurality of views; generating a view plane at a specific point by recording the calculated pixel value on one MPI layer determined based on the spatial position of the corresponding photographed object among a plurality of MPI layers; and generating MPI data by additionally recording the pixel value for the view.

Abstract: Depth image generation is improved by more efficient encoding using video codecs. The mapping of the depth to the luma channel is performed by not using all bits available, and with the remaining bits, a depth scaling factor is generated and incorporated into the bilinear interpolation algorithm used during rasterization. A normal filtering procedure is described, where the positions of vertices are adjusted according to the normal estimated from the surface pixels. After decoding the depth image, the pixels related to the surface of a triangle are collected and used to estimate a plane and the normal of the plane. The normal is compared to the normal obtained from the plane defined by the three vertices of the triangle. If there is no match, the positions of the vertices are adjusted to match the estimated normal from the pixels' surfaces. The adjustment can follow an iterative minimization process.

Abstract: An image processing apparatus obtains multiple silhouette images corresponding to the images captured by multiple image capturing apparatuses for corresponding frames forming a moving image; in a case where an abnormality is detected in at least one of the plurality of images, identifies a frame and an image capturing apparatus corresponding to the image in which the abnormality is detected; and generates three-dimensional shape data of the object by using the plurality of images, wherein in a case of generating the three-dimensional shape data in a plurality of frames corresponding to a period from detecting the abnormality to satisfying a predetermined condition, the three-dimensional shape data is generated by not using the image corresponding to the identified image capturing apparatus.