Abstract: A method includes receiving an input image. The input image corresponds to one or more masked regions to be inpainted. The method includes providing the input image to a first neural network. The first neural network outputs a first inpainted image at a first resolution, and the one or more masked regions are inpainted in the first inpainted image. The method includes creating a second inpainted image by increasing a resolution of the first inpainted image from the first resolution to a second resolution. The second resolution is greater than the first resolution such that the one or more inpainted masked regions have an increased resolution. The method includes providing the second inpainted image to a second neural network. The second neural network outputs a first refined inpainted image at the second resolution, and the first refined inpainted image is a refined version of the second inpainted image.

Abstract: A media application generates training data that includes a first set of media items and a second set of media items, where the first set of media items correspond to the second set of media items and include distracting objects that are manually segmented. The media application trains a segmentation machine-learning model based on the training data to receive a media item with one or more distracting objects and to output a segmentation mask for one or more segmented objects that correspond to the one or more distracting objects.

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to train and use a machine-learning model to colorize a grayscale image that depicts a person. In some implementations, a computer-implemented method includes receiving the grayscale image. The method further includes generating a colorized image based on the grayscale image as output of a trained convolutional neural network (CNN) by providing the grayscale image as input to the trained CNN. In some implementations, the trained CNN performs part segmentation to detect one or more parts of the person and colorizes the grayscale image.

Abstract: A method for a computer system includes receiving a first camera image of a 3D object having sensor markers, captured from a first location, at a first instance, receiving a second camera image of the 3D object from a second location, at a different instance, determining points from the first camera image representing sensor markers of the 3D object, determining points from the second camera image representing sensor markers of the 3D object, determining approximate correspondence between points from the first camera image and points from the second camera image, determining approximate 3D locations some sensor markers of the 3D object, and rendering an image including the 3D object in response to the approximate 3D locations.

Abstract: A method for a computer system includes receiving a first camera image of a 3D object having sensor markers, captured from a first location, at a first instance, receiving a second camera image of the 3D object from a second location, at a different instance, determining points from the first camera image representing sensor markers of the 3D object, determining points from the second camera image representing sensor markers of the 3D object, determining approximate correspondence between points from the first camera image and points from the second camera image, determining approximate 3D locations some sensor markers of the 3D object, and rendering an image including the 3D object in response to the approximate 3D locations.