Abstract: A modeling system accesses a two-dimensional (2D) input image displayed via a user interface, the 2D input image depicting, at a first view, a first object. At least one region of the first object is not represented by pixel values of the 2D input image. The modeling system generates, by applying a 3D representation generation model to the 2D input image, a three-dimensional (3D) representation of the first object that depicts an entirety of the first object including the first region. The modeling system displays, via the user interface, the 3D representation, wherein the 3D representation is viewable via the user interface from a plurality of views including the first view.

Abstract: Various disclosed embodiments are directed to deriving an albedo output image from an input image based on deriving an inverse shading map. For example, an input image can be a photograph of a human face (i.e., the geometric features) with RGB values representing the color values of the face as well as pixels representing shadows (i.e., the shadow features) underneath the chin of the human face. The inverse shading map may be a black and white pixel value image that contains pixels representing the same human face without the RGB values and the shadows underneath the chin. The inverse shading map thus relies on the geometric space, rather than RGB space. Geometric space, for example, allows embodiments to capture the geometric features of a face, as opposed to those geometric features' RGB or shadow details.

Abstract: The present disclosure relates to a system that utilizes neural networks to generate looping animations from still images. The system fits a 3D model to a pose of a person in a digital image. The system receives a 3D animation sequence that transitions between a starting pose and an ending pose. The system generates, utilizing an animation transition neural network, first and second 3D animation transition sequences that respectively transition between the pose of the person and the starting pose and between the ending pose and the pose of the person. The system modifies each of the 3D animation sequence, the first 3D animation transition sequence, and the second 3D animation transition sequence by applying a texture map. The system generates a looping 3D animation by combining the modified 3D animation sequence, the modified first 3D animation transition sequence, and the modified second 3D animation transition sequence.

Abstract: Techniques for modeling secondary motion based on three-dimensional models are described as implemented by a secondary motion modeling system, which is configured to receive a plurality of three-dimensional object models representing an object. Based on the three-dimensional object models, the secondary motion modeling system determines three-dimensional motion descriptors of a particular three-dimensional object model using one or more machine learning models. Based on the three-dimensional motion descriptors, the secondary motion modeling system models at least one feature subjected to secondary motion using the one or more machine learning models. The particular three-dimensional object model having the at least one feature is rendered by the secondary motion modeling system.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify two-dimensional images via scene-based editing using three-dimensional representations of the two-dimensional images. For instance, in one or more embodiments, the disclosed systems utilize three-dimensional representations of two-dimensional images to generate and modify shadows in the two-dimensional images according to various shadow maps. Additionally, the disclosed systems utilize three-dimensional representations of two-dimensional images to modify humans in the two-dimensional images. The disclosed systems also utilize three-dimensional representations of two-dimensional images to provide scene scale estimation via scale fields of the two-dimensional images. In some embodiments, the disclosed systems utilizes three-dimensional representations of two-dimensional images to generate and visualize 3D planar surfaces for modifying objects in two-dimensional images.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify two-dimensional images via scene-based editing using three-dimensional representations of the two-dimensional images. For instance, in one or more embodiments, the disclosed systems utilize three-dimensional representations of two-dimensional images to generate and modify shadows in the two-dimensional images according to various shadow maps. Additionally, the disclosed systems utilize three-dimensional representations of two-dimensional images to modify humans in the two-dimensional images. The disclosed systems also utilize three-dimensional representations of two-dimensional images to provide scene scale estimation via scale fields of the two-dimensional images. In some embodiments, the disclosed systems utilizes three-dimensional representations of two-dimensional images to generate and visualize 3D planar surfaces for modifying objects in two-dimensional images.

Abstract: Apparatuses, systems, and techniques are presented to perform monocular view synthesis of a dynamic scene. Single and multi-view depth information can be determined for a collection of images of a dynamic scene, and a blender network can be used to combine image features for foreground, background, and missing image regions using fused depth maps inferred form the single and multi-view depth information.

Abstract: A surgical navigation system according to one embodiment may comprise: an electromagnetic wave generation unit; a first detection unit attached to a surgical site of an object to detect a position attached to the surgical site; a second detection unit installed in a patient-specific surgical guide instrument inserted into the surgical site to receive the electromagnetic wave and detect the position of the patient-specific surgical guide instrument; a third detection unit installed in the surgical instrument inserted into the surgical site to detect the position of the surgical instrument; an information processing unit for registering the position of the first detection unit and the position of the third detection unit and for tracking the position of the surgical instrument on the basis of the position of the first detection unit attached to the surgical site, by setting the position of the patient-specific surgical guide instrument as a reference position when the patient-specific surgical guide instrument

Abstract: A smart screw according to an embodiment may comprise: a screw main body which penetrates an artificial joint including a shell disposed on a hip joint of an object and a liner disposed on the inner surface of the shell and is then inserted into the hip joint; a transducer including a coupling layer that senses a sound wave signal reflected from the liner, a piezo-electric layer formed to determine a frequency of the sound wave signal, and a sound absorbing layer for absorbing the sound wave signal; and a processing module for generating a sound wave signal toward the liner and receiving the sound wave signal sensed by the coupling layer, measuring the thickness of the liner on the basis of the received sound wave signal, and transferring data about the measured thickness of the liner to the outside.

Abstract: The present invention relates to Akkermansia muciniphila SNUG-61027 strain (accession number KCTC 13530BP) and use thereof, specifically, a composition for suppressing appetite or preventing, ameliorating, alleviating or treating metabolic diseases, comprising the strain, or a culture solution thereof, etc. or a B2UM07 protein isolated therefrom as an active ingredient, and use thereof for suppressing appetite or preventing, ameliorating, alleviating or treating metabolic diseases, and a method of suppressing appetite or preventing, ameliorating, alleviating or treating metabolic diseases using the same are provided. Through this, among the anti-obesity effects, not only weight reduction and glucose homeostasis regulation, but also the effect on brown fat and the effect of secreting appetite regulating hormones are exhibited.

Abstract: A smart screw according to an embodiment may comprise: a screw main body which penetrates an artificial joint including a shell disposed on a hip joint of an object and a liner disposed on the inner surface of the shell and is then inserted into the hip joint; a transducer including a coupling layer that senses a sound wave signal reflected from the liner, a piezo-electric layer formed to determine a frequency of the sound wave signal, and a sound absorbing layer for absorbing the sound wave signal; and a processing module for generating a sound wave signal toward the liner and receiving the sound wave signal sensed by the coupling layer, measuring the thickness of the liner on the basis of the received sound wave signal, and transferring data about the measured thickness of the liner to the outside.

Abstract: A surgical navigation system for registering coordinates of a patient-customized tool, according to one embodiment, comprises: an electromagnetic wave generation unit for generating an electromagnetic wave; an electromagnetic sensor provided in a patient-customized tool and including a coil through which the electromagnetic wave passes; and a processing unit for calculating the position and the orientation of the electromagnetic sensor on the basis of magnetic flux, which is interlinked with the coil, and calculating the position and the orientation of the patient-customized tool on the basis of the position and the orientation of the electromagnetic sensor.

Abstract: A powerless electromagnetic sensor according to an embodiment may comprise: a wireless power receiver for receiving a power signal from an external data receiver unit by using one resonance frequency selected from a plurality of resonance frequencies set therefor; a digital signal converter for converting the received power signal into a digital signal; and a processor for converting the power signal into a magnetic flux density value corresponding to the selected resonance frequency on the basis of the digital signal, and calculating the position and orientation of the electromagnetic sensor on the basis of the converted magnetic flux density value.

Abstract: A surgical navigation system according to one embodiment may comprise: an electromagnetic wave generation unit; a first detection unit attached to a surgical site of an object to detect a position attached to the surgical site; a second detection unit installed in a patient-specific surgical guide instrument inserted into the surgical site to receive the electromagnetic wave and detect the position of the patient-specific surgical guide instrument; a third detection unit installed in the surgical instrument inserted into the surgical site to detect the position of the surgical instrument; an information processing unit for registering the position of the first detection unit and the position of the third detection unit and for tracking the position of the surgical instrument on the basis of the position of the first detection unit attached to the surgical site, by setting the position of the patient-specific surgical guide instrument as a reference position when the patient-specific surgical guide instrument

Abstract: The present examples relate to a liquid crystal display device with a repair function. The present examples repair a defect of a line or a defect of a pixel, using a specialized data signal structure, wherein the data signal structure integrates channel data, which is required for channel driving of a liquid crystal display element, and repair amplifier data, which is used for repairing a defect of a line and/or a pixel. Thus, examples have a better repair function than an alternative liquid crystal display device.

Abstract: An apparatus and a method that quickly detect an error that may occur due to an external noise occurrence during display of image data on a screen of an image display device, and that control a strobe signal output to prevent a screen defect from being displayed on the display device screen.

Abstract: Provided is a garnet-based phosphor doped with thorium and a light emitting device using the same. In particular, a garnet-based phosphor having superior light characteristics and heat stability by using thorium as an activator, when compared to a conventional garnet phosphor using cerium as an activator, and a light emitting device using the same as a light source are provided.

Abstract: A phosphor and a light emitting device containing the phosphor are provided. According to an embodiment, the phosphor is expressed in a chemical formula of LxMyCz1Nz2:Aa where L is at least one of an alkaline earth metal, a transition metal, Zn, Cd, Al, Ga, In, Ti, Ge, and Sn; M is at least one of B, Si, P, S, F, Cl, I, and Se; and A is at least one of an alkaline rare earth metal and the transition metal, and where 0<x?5, 0?y?5, 1?z1?10, 1?z2?10, and 0<a?1.

Abstract: An apparatus and a method that quickly detect an error that may occur due to an external noise occurrence during display of image data on a screen of an image display device, and that control a strobe signal output to prevent a screen defect from being displayed on the display device screen.

Abstract: The present examples relate to a liquid crystal display device with a repair function. The present examples repair a defect of a line or a defect of a pixel, using a specialized data signal structure, wherein the data signal structure integrates channel data, which is required for channel driving of a liquid crystal display element, and repair amplifier data, which is used for repairing a defect of a line and/or a pixel. Thus, examples have a better repair function than an alternative liquid crystal display device.