Abstract: Embodiments are disclosed for performing wire segmentation of images using machine learning. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input image, generating, by a first trained neural network model, a global probability map representation of the input image indicating a probability value of each pixel including a representation of wires, and identifying regions of the input image indicated as including the representation of wires. The disclosed systems and methods further comprise, for each region from the identified regions, concatenating the region and information from the global probability map to create a concatenated input, and generating, by a second trained neural network model, a local probability map representation of the region based on the concatenated input, indicating pixels of the region including representations of wires. The disclosed systems and methods further comprise aggregating local probability maps for each region.

Abstract: A device automatically segments an image into different regions and automatically adjusts perceived exposure-levels or other characteristics associated with each of the different regions, to produce pictures that exceed expectations for the type of optics and camera equipment being used and in some cases, the pictures even resemble other high-quality photography created using professional equipment and photo editing software. A machine-learned model is trained to automatically segment an image into distinct regions. The model outputs one or more masks that define the distinct regions. The mask(s) are refined using a guided filter or other technique to ensure that edges of the mask(s) conform to edges of objects depicted in the image. By applying the mask(s) to the image, the device can individually adjust respective characteristics of each of the different regions to produce a higher-quality picture of a scene.

Abstract: An apparatus and method are disclosed to produce a stereoscopic image with a hemispherical field of view. In an implementation, the apparatus includes an optical arrangement to receive first light rays from a first fisheye lens and second light rays from a second fisheye lens. The first fisheye lens and the second fisheye lens are positioned adjacent to each other and an object side of each of the first and second fisheye lenses faces a first plane. The optical arrangement is to direct the first light rays and the second light rays onto an image sensor and bend optical axes of the first and second light rays such that the first light rays are projected onto the image sensor alongside the second light rays.

Abstract: An apparatus and method are disclosed to produce a stereoscopic image with a hemispherical field of view. In an implementation, the apparatus includes an optical arrangement to receive first light rays from a first fisheye lens and second light rays from a second fisheye lens. The first fisheye lens and the second fisheye lens are positioned adjacent to each other and an object side of each of the first and second fisheye lenses faces a first plane. The optical arrangement is to direct the first light rays and the second light rays onto an image sensor and bend optical axes of the first and second light rays such that the first light rays are projected onto the image sensor alongside the second light rays.

Abstract: A computer-implemented method includes dividing an image into one or more image channels for image compression. The method also includes dividing one or more of the image channels into one or more blocks. At least one of the blocks includes floating point representations of pixel values included in the block. The method also includes converting the floating point representations of pixel values into integer representations such that the sign of each floating point representation is preserved. The method also includes storing the difference of adjacent integer representations as a compressed version of the image.

Abstract: Changes to the outputs of a dependency graph, which has attribute nodes and operator nodes, are detected by forming product proxies for the outputs of dependency graph nodes. The product proxies can be formed by entering information about the dependency graph into a hashing algorithm. Before and after product proxies are then used to determine if the outputs have changed.

Abstract: Changes to the outputs of a dependency graph, which has attribute nodes and operator nodes, are detected by forming product proxies for the outputs of dependency graph nodes. The product proxies can be formed by entering information about the dependency graph into a hashing algorithm. Before and after product proxies are then used to determine if the outputs have changed.

Abstract: Changes to the outputs of a dependency graph, which has attribute nodes and operator nodes, are detected by forming product proxies for the outputs of dependency graph nodes. The product proxies can be formed by entering information about the dependency graph into a hashing algorithm. Before and after product proxies are then used to determine if the outputs have changed.