Abstract: A system is configured to obtain image data of a joint of a patient; determine that the joint includes an existing implant; and one or both of generate an identification of a type for the existing implant and generate a pre-implant, morbid approximation of the joint.

Abstract: A processor-implemented method with three-dimensional (3D) modeling includes: determining a type of movement of an object detected in an image received from a sensor, based on a variability of a position of the object and a variability of a shape of the object; segmenting the object into one or more chunks each corresponding to a unit of movement, based on the determined type of movement; correcting the determined type of movement based on a change in position of one or more feature points of the one or more chunks of the object in the image; determining a state of the movement of the object based on the corrected type of the movement of the object; correcting a pose of the sensor based on a state of the object; and updating a pose for each of the one or more chunks of the object based on the determined state of the object and the corrected pose of the sensor.

Abstract: The subject technology causes display, at the client device, a set of augmented reality content items generated by the first augmented reality content generator. The subject technology receives, at the client device, a second selection of the particular augmented reality content item corresponding to the destination geolocation. The subject technology causes display, at the client device, a second set of augmented reality content items generated by the first augmented reality content generator. The subject technology receives, at the client device, a second selection of the second set of augmented reality content items. The subject technology causes display, at the client device, a third set of augmented reality content items generated by the first augmented reality content generator, the third set of augmented reality content items comprising at least one activity or location associated with the destination geolocation and a selected period of time.

Abstract: There is a region of interest of a synthetic image depicting an object from a class of objects. A trained neural image generator, having been trained to map embeddings from a latent space to photorealistic images of objects in the class, is accessed. A first embedding is computed from the latent space, the first embedding corresponding to an image which is similar to the region of interest while maintaining photorealistic appearance. A second embedding is computed from the latent space, the second embedding corresponding to an image which matches the synthetic image. Blending of the first embedding and the second embedding is done to form a blended embedding. At least one output image is generated from the blended embedding, the output image being more photorealistic than the synthetic image.

Abstract: A computer implemented method of navigating a digital representation of a spatial environment by a user in which a portion of the digital representation is rendered by a rendering computer system for visualization by the user. The method including accessing a digital model of the spatial environment including a specification of each of a plurality of virtual resources in the spatial environment, each specification identifying at least a location of a resource in the spatial environment and at least one trigger criterion for determining when a resource is accessed by the user; monitoring the satisfaction of trigger criteria for the plurality of virtual resources; and responsive to the monitoring, determining the portion of the digital representation for rendering by the rendering computer system for visualization by the user.

Abstract: Methods and media for analyzing a patient's dental arches in order to generate a treatment plan for the dentition when the patient is missing one or more teeth. The methods and media can include indentifying one or more missing teeth, and estimating one or more dimensions of the one or more missing teeth.

Abstract: A processor device that is an image processing apparatus functions as an image obtaining unit that obtains an endoscopic image obtained by capturing an image of a photographic subject, a biological information calculation unit that calculates biological information concerning the photographic subject by using the endoscopic image or a display image generated by using the endoscopic image, and a texture processing unit that superimposes a plurality of textures representing the biological information on the endoscopic image or the display image and shows a boundary between adjacent textures.

Abstract: A computer implemented method for generating a 3D printable model of a patient specific anatomic feature from 2D medical images is provided. A 3D image is automatically generated from a set of 2D medical images. A machine learning based image segmentation technique is used to segment the generated 3D image. A 3D printable model of the patient specific anatomic feature is created from the segmented 3D image.

Abstract: An image rendering method for rendering a pixel at a viewpoint includes: for a first element of a virtual scene, having a predetermined surface at a position within that scene, evaluating whether to render a pixel corresponding to the first element using at least a first machine learning system having been trained to generate an illuminance output representative of the lighting of the predetermined surface at the position, or using an alternative rendering approach, and rendering the pixel according to which of the at least first machine learning system and the alternative rendering approach are chosen in the evaluating step; where the evaluating step comprises obtaining a confidence value from the at least first machine learning system indicative of the accuracy of the illuminance output, the machine learning system having been trained to generate the confidence value in conjunction with the illuminance output, and the rendering step comprises using the alternative rendering approach if the confidence value

Abstract: A path planning method based on dynamic contour offset discretization and for spatial curved-surface printing is provided. Firstly, transversal equal slicing is carried out on a target model, and single/double contours are labeled; secondly, central slicing is carried out on the model, curvature contours are discretized, feature values of contour offsets of slice layers are calculated on the basis of a surface contour curvature of the model, and dynamic offset filling for inner contours of horizontal slices is realized; then longitudinal equal slicing is carried out on the slices, and spatial discrete points of the target model are obtained; and finally, virtual double contours are constructed for the single contours, and labeling processing for the discrete points is carried out, so that a discretized three-dimensional spatial equidistant lattice of the target model is obtained.

Abstract: A method of automatically displaying a predetermined set of print attributes of a print job, the method including receiving an image of a first printed sheet, the first printed sheet including one or more at least partial machine-readable codes, the one or more at least partial machine-readable codes encoded with data related to the predetermined set of print attributes, decoding the data from the one or more at least partial machine-readable codes, determining if the data includes all of the print attributes in the predetermined set of print attributes, and if the data includes all of the print attributes in the predetermined set of print attributes, displaying the data using augmented reality (AR) over the first printed sheet.

Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that can render a virtual object in a digital image by using a source-specific-lighting-estimation-neural network to generate three-dimensional (“3D”) lighting parameters specific to a light source illuminating the digital image. To generate such source-specific-lighting parameters, for instance, the disclosed systems utilize a compact source-specific-lighting-estimation-neural network comprising both common network layers and network layers specific to different lighting parameters. In some embodiments, the disclosed systems further train such a source-specific-lighting-estimation-neural network to accurately estimate spatially varying lighting in a digital image based on comparisons of predicted environment maps from a differentiable-projection layer with ground-truth-environment maps.

Abstract: Various methods and systems are provided for authoring and presenting 3D presentations. Generally, an augmented or virtual reality device for each author, presenter and audience member includes 3D presentation software. During authoring mode, one or more authors can use 3D and/or 2D interfaces to generate a 3D presentation that choreographs behaviors of 3D assets into scenes and beats. During presentation mode, the 3D presentation is loaded in each user device, and 3D images of the 3D assets and corresponding asset behaviors are rendered among the user devices in a coordinated manner. As such, one or more presenters can navigate the scenes and beats of the 3D presentation to deliver the 3D presentation to one or more audience members wearing augmented reality headsets.

Abstract: The present disclosure generally relates to systems and methods for three-dimensional image sensing. More specifically, and without limitation, this disclosure relates to systems and methods for detecting three-dimensional images, and using asynchronous image sensors for detecting the same.

Abstract: A virtual filler is inserted in a virtual model of a dental site between a first tooth and a second tooth in the virtual model. One or more of the first tooth or the second tooth represent a natural tooth of a patient. Points of the first tooth, the second tooth and the virtual filler are transformed into a voxel volume. A geometry of an updated virtual filler is determined by transforming a surface of the voxel volume into a polygonal mesh.

Abstract: Disclosed herein is a method of supporting implant surgery in a server, which includes obtaining a subject's oral CT image scanned with a guide model inserted into an oral cavity of the subject, the guide model being manufactured to a certain standard to group human teeth in any range so that the teeth belong to at least one group and to cover a tooth position of a corresponding group, the guide model including a marker made of a radiopaque or radiation semipermeable material, loading a library as information about the standard of the guide model, identifying the marker in the oral CT image, and generating a library matching CT image by matching the oral CT image with the library based on the marker included in the library and the marker identified in the oral CT image, and planning implant surgery of the subject using the library matching CT image.

Abstract: An operation system for industrial machinery comprises: an information acquisition unit which acquires machine identification information corresponding to an industrial machine; a machine identification unit which identifies the industrial machine on the basis of the acquired machine identification information; a model projection unit which projects a model corresponding to the identified industrial machine into a virtual space; a distance/direction calculation unit which calculates the distance and direction, of a user observing the model, with respect to the projected model; a gesture observation unit which observes the gesture of the user as an instruction from the user to the identified industrial machine; an instruction determination unit which determines whether or not a user can give an instruction; and an operation instruction unit which operates the identified industrial machine on the basis of the observed gesture of the user, when the determination result is positive.

Abstract: An apparatus for evaluating a quality for image capture comprises a stored (101) for storing a model of a scene and a capture circuit (105) for generating virtual captured images for a camera configuration by rendering from the model. A depth generation circuit (107) generates model depth data from the model and a depth estimation circuit (111) generates estimated depth data from the virtual captured images. A first synthesis circuit (109) and a second synthesis circuit (113) generates first and second view images for test poses by processing the virtual captured images based on the model depth data or estimated depth data respectively. A reference circuit (103) generates reference images for the f test poses by rendering based on the model. A quality circuit (115) generates a quality metric based on a comparison of the first view images, the second view images, and the reference images.

Abstract: A system includes an intraoral scanner and a computing device. The intraoral scanner generates an intraoral scan of a dental site. The computing device processes an input comprising data from the intraoral scan using a trained machine learning model that has been trained to classify regions of dental sites, wherein the trained machine learning model generates an output comprising, for each point in the intraoral scan, an indication as to whether the point belongs to a first dental class that represents excess material. The computing device determines, based on the output, one or more points in the intraoral scan that are classified as excess material. The computing device then hides or removes, from at least one of the intraoral scan or a virtual three-dimensional (3D) model generated using the intraoral scan, data for the one or more points that are classified as excess material.

Abstract: Approaches in accordance with various embodiments provide for fluid simulation with substantially reduced time and memory requirements with respect to conventional approaches. In particular, various embodiments can perform time and energy efficient, large scale fluid simulation on processing hardware using a method that does not solve for the Navier-Stokes equations to enforce incompressibility. Instead, various embodiments generate a density tensor and rigid body map tensor for a large number of particles contained in a sub-domain. Collectively, the density tensor and rigid body map may represent input channels of a network with three spatial-dimensions. The network may apply a series of operations to the input channels to predict an updated position and updated velocity for each particle at the end of a frame. Such approaches can handle tens of millions of particles within a virtually unbounded simulation domain, as compared to classical approaches that solve for the Navier-Stokes equations.