Abstract: A computer-implemented method includes receiving a real two-dimensional medical image of a patient, processing the real two-dimensional medical image with a computer-implemented generator configured to transfer the real two-dimensional medical image from a real image domain into a synthetic image domain, and analyzing the two-dimensional medical image transferred into the synthetic image domain with a machine-learning model. The machine-learning model was trained with a collection of synthetic two-dimensional medical images generated from real three-dimensional medical images.

Abstract: A display device includes: a display medium having a screen area in which pixels are disposed at regular intervals; and a controller that causes the display medium to display an image. The controller is configured to perform refresh process on target pixels that are included in a different pixel pattern for each predetermined refresh cycle. The target pixels being of the pixels disposed in the screen area and being distributed at intervals wider than the regular intervals.

Abstract: An apparatus includes first, second, and third units. The first unit is configured to obtain a first three-dimensional point based on an initial start point of a motion vector in one image of a stereo image and a point corresponding to the initial start point in the other image of the stereo image. The second unit is configured to obtain a second three-dimensional point based on an initial end point of the motion vector in the one image and a point corresponding to the initial end point in the other image. The third unit is configured to obtain, based on the first and second three-dimensional points, a third three-dimensional point for which a camerawork motion component has been removed from the second three-dimensional point and obtain, based on the third and first three-dimensional points, an amount of shake in the stereo image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating high-resolution images using self-attention based neural networks. One of the systems includes a neural network configured to generate images, the neural network comprising a sequence of one or more first network blocks followed by a sequence of one or more second network blocks, wherein: each first network block is configured to perform operations comprising: applying a self-attention mechanism over at least a subset of first elements of a first block input to generate an updated first block input; and upsampling the updated first block input to generate a first block output; and each second network block is configured to perform operations comprising: processing a second block input using one or more neural network layers to generate an updated second block input; and upsampling the updated second block input to generate a second block output.

Abstract: An automated method for generating a prosthesis from a three dimensional (“3D”) scan data, the method includes generating an intermediate surface of the prosthesis extending toward an outside of a prepared tooth from a margin line of the prepared tooth in the 3D scan data, generating an inner surface of the prosthesis by determining a gap from a surface of the prepared tooth, generating an outer surface of the prosthesis and connecting the outer surface of the prosthesis and the intermediate surface of the prosthesis.

Abstract: A technique for performing ray tracing operations is provided. The technique includes detecting intersection of a ray with a split bounding volume of an instance of a bounding volume hierarchy; determining whether the split bounding volume meets an instance traversal limiting criterion; and continuing BVH traversal based on the determining.

Abstract: Disclosed are a positioning method including: obtaining, by a device for providing a positioning function, multi-source wireless signal data from a collection data database (DB); generating, by the device, a matching map using the multi-source wireless signal data; generating, by the device, a matching map image corresponding to the matching map; generating, by the device, a classification model for positioning that outputs a labeling value of the matching map image when the matching map image is input; and performing, by the device, positioning based on a labeling value of a classified image that is output as a result of inputting the matching map image to the classification model for positioning, and a positioning device for providing a positioning function.