Abstract: Techniques are disclosed for deep neural network (DNN) based interactive image matting. A methodology implementing the techniques according to an embodiment includes generating, by the DNN, an alpha matte associated with an image, based on user-specified foreground region locations in the image. The method further includes applying a first DNN subnetwork to the image, the first subnetwork trained to generate a binary mask based on the user input, the binary mask designating pixels of the image as background or foreground. The method further includes applying a second DNN subnetwork to the generated binary mask, the second subnetwork trained to generate a trimap based on the user input, the trimap designating pixels of the image as background, foreground, or uncertain status. The method further includes applying a third DNN subnetwork to the generated trimap, the third subnetwork trained to generate the alpha matte based on the user input.

Abstract: Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.

Abstract: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for generating an ambient occlusion (AO) map for a 2D image that can be combined with the 2D image to adjust the contrast of the 2D image based on the geometric information in the 2D image. In embodiments, using a trained neural network, an AO map for a 2D image is automatically generated without any predefined 3D scene information. Optimizing the neural network to generate an estimated AO map for a 2D image requires training, testing, and validating the neural network using a synthetic dataset comprised of pairs of images and ground truth AO maps rendered from 3D scenes. By using an estimated AO map to adjust the contrast of a 2D image, the contrast of the image can be adjusted to make the image appear lifelike by modifying the shadows and shading in the image based on the ambient lighting present in the image.

Abstract: Techniques are disclosed for deep neural network (DNN) based interactive image matting. A methodology implementing the techniques according to an embodiment includes generating, by the DNN, an alpha matte associated with an image, based on user-specified foreground region locations in the image. The method further includes applying a first DNN subnetwork to the image, the first subnetwork trained to generate a binary mask based on the user input, the binary mask designating pixels of the image as background or foreground. The method further includes applying a second DNN subnetwork to the generated binary mask, the second subnetwork trained to generate a trimap based on the user input, the trimap designating pixels of the image as background, foreground, or uncertain status. The method further includes applying a third DNN subnetwork to the generated trimap, the third subnetwork trained to generate the alpha matte based on the user input.

Abstract: One embodiment of a bucket drill and soil screen apparatus consists of a mast (9) attached to a prime mover vehicle (7). A carriage (10) and hydraulic motor (12) slide vertically along the mast from which an attached kelly bar (14) and drilling bucket (15) are rotated and lowered into the ground. A kickout assembly (13) lifts drilling bucket (15) outward in an arc. Soil and cultural artifacts are transferred to a screen basket (20) by rotating open the drilling bucket through a latch and hinge. The screen basket is lifted to its screening position and rotated around a central axis to facilitate the passing of fine soil particles through the hardware cloth walls of the basket. Cultural artifacts retained in the screen basket are transferred to a fixed sorting screen (22) by rotating the screen basket to its dump position.

Abstract: A table layout determination system implemented on a computing device obtains an image of a table having multiple cells. The table layout determination system includes a row prediction machine learning system that generates, for each of multiple rows of pixels in the image of the table, a probability of the row being a row separator, and a column prediction machine learning system generates, for each of multiple columns of pixels in the image of the table, a probability of the column being a column separator. An inference system uses these probabilities of the rows being row separators and the columns being column separators to identify the row separators and column separators for the table. These row separators and column separators are the layout of the table.

Abstract: Compositing aware digital image search techniques and systems are described that leverage machine learning. In one example, a compositing aware image search system employs a two-stream convolutional neural network (CNN) to jointly learn feature embeddings from foreground digital images that capture a foreground object and background digital images that capture a background scene. In order to train models of the convolutional neural networks, triplets of training digital images are used. Each triplet may include a positive foreground digital image and a positive background digital image taken from the same digital image. The triplet also contains a negative foreground or background digital image that is dissimilar to the positive foreground or background digital image that is also included as part of the triplet.

Abstract: Techniques are disclosed for deep neural network (DNN) based interactive image matting. A methodology implementing the techniques according to an embodiment includes generating, by the DNN, an alpha matte associated with an image, based on user-specified foreground region locations in the image. The method further includes applying a first DNN subnetwork to the image, the first subnetwork trained to generate a binary mask based on the user input, the binary mask designating pixels of the image as background or foreground. The method further includes applying a second DNN subnetwork to the generated binary mask, the second subnetwork trained to generate a trimap based on the user input, the trimap designating pixels of the image as background, foreground, or uncertain status. The method further includes applying a third DNN subnetwork to the generated trimap, the third subnetwork trained to generate the alpha matte based on the user input.

Abstract: A modular electronics package is disclosed that includes a first and second electronics packages, with each of the first and second electronics packages including a metallized insulating substrate and a solid-state switching device positioned on the metallized insulating substrate, the solid-state switching device comprising a plurality of contact pads electrically coupled to the first conductor layer of the metallized insulating substrate. A conductive joining material is positioned between the first electronics package and the second electronics package to electrically connect them together. The first electronics package and the second electronics package are stacked with one another to form a half-bridge unit cell, with the half-bridge unit cell having a current path through the solid-state switching device in the first electronics package and a close coupled return current path through the solid-state switching device in the second electronics package in opposite flow directions.

Abstract: Compositing aware digital image search techniques and systems are described that leverage machine learning. In one example, a compositing aware image search system employs a two-stream convolutional neural network (CNN) to jointly learn feature embeddings from foreground digital images that capture a foreground object and background digital images that capture a background scene. In order to train models of the convolutional neural networks, triplets of training digital images are used. Each triplet may include a positive foreground digital image and a positive background digital image taken from the same digital image. The triplet also contains a negative foreground or background digital image that is dissimilar to the positive foreground or background digital image that is also included as part of the triplet.

Abstract: Techniques and systems are described for style-aware patching of a digital image in a digital medium environment. For example, a digital image creation system generates style data for a portion to be filled of a digital image, indicating a style of an area surrounding the portion. The digital image creation system also generates content data for the portion indicating content of the digital image of the area surrounding the portion. The digital image creation system selects a source digital image based on similarity of both style and content of the source digital image at a location of the patch to the style data and content data. The digital image creation system transforms the style of the source digital image based on the style data and generates the patch from the source digital image in the transformed style for incorporation into the portion to be filled of the digital image.

Abstract: Fill techniques as implemented by a computing device are described to perform hole filling of a digital image. In one example, deeply learned features of a digital image using machine learning are used by a computing device as a basis to search a digital image repository to locate the guidance digital image. Once located, machine learning techniques are then used to align the guidance digital image with the hole to be filled in the digital image. Once aligned, the guidance digital image is then used to guide generation of fill for the hole in the digital image. Machine learning techniques are used to determine which parts of the guidance digital image are to be blended to fill the hole in the digital image and which parts of the hole are to receive new content that is synthesized by the computing device.

Abstract: Disclosed systems and methods generate page segmented documents from unstructured vector graphics documents. The page segmentation application executing on a computing device receives as input an unstructured vector graphics document. The application generates an element proposal for each of many areas on a page of the input document tentatively identified as being page elements. The page segmentation application classifies each of the element proposals into one of a plurality of defined type of categories of page elements. The page segmentation application may further refine at least one of the element proposals and select a final element proposal for each element within the unstructured vector document. One or more of the page segmentation steps may be performed using a neural network.

Abstract: Fill techniques as implemented by a computing device are described to perform hole filling of a digital image. In one example, deeply learned features of a digital image using machine learning are used by a computing device as a basis to search a digital image repository to locate the guidance digital image. Once located, machine learning techniques are then used to align the guidance digital image with the hole to be filled in the digital image. Once aligned, the guidance digital image is then used to guide generation of fill for the hole in the digital image. Machine learning techniques are used to determine which parts of the guidance digital image are to be blended to fill the hole in the digital image and which parts of the hole are to receive new content that is synthesized by the computing device.

Abstract: A pipe rehabilitation system and/or robot can be used inside a pipe to measure characteristics of branch conduits, install plugs into branch conduits before the pipe is lined with a liner, remove portions of plugs and liners after lining to restore fluid communication between the pipe and branch conduits, and/or install fittings into the branch conduits to connect the liner to the branch conduits. A probe can measure characteristics of a branch conduit. A tool can install plugs and/or fittings into the branch conduits. A linkage can connect a tool to a robotic tractor so that the connected elements can navigate through a main pipe. A visualization system can aid in aligning a robot with a branch conduit. Height-adjustable braces can support robotic tools in a pipe. A plug can include integrated locating features and/or movable parts that enable expanding the plug to seal with the branch conduit.

Abstract: A system that is configured to coordinate student dismissal at end of day. The system may use a central server to maintain information across multiple different devices, each for different functions in the dismissal process.

Abstract: A modular electronics package is disclosed that includes a first and second electronics packages, with each of the first and second electronics packages including a metallized insulating substrate and a solid-state switching device positioned on the metallized insulating substrate, the solid-state switching device comprising a plurality of contact pads electrically coupled to the first conductor layer of the metallized insulating substrate. A conductive joining material is positioned between the first electronics package and the second electronics package to electrically connect them together. The first electronics package and the second electronics package are stacked with one another to form a half-bridge unit cell, with the half-bridge unit cell having a current path through the solid-state switching device in the first electronics package and a close coupled return current path through the solid-state switching device in the second electronics package in opposite flow directions.

Abstract: Methods and systems are provided for generating mattes for input images. A neural network system can be trained where the training includes training a first neural network that generates mattes for input images where the input images are synthetic composite images. Such a neural network system can further be trained where the training includes training a second neural network that generates refined mattes from the mattes produced by the first neural network. Such a trained neural network system can be used to input an image and trimap pair for which the trained system will output a matte. Such a matte can be used to extract an object from the input image. Upon extracting the object, a user can manipulate the object, for example, to composite the object onto a new background.

Abstract: A table layout determination system implemented on a computing device obtains an image of a table having multiple cells. The table layout determination system includes a row prediction machine learning system that generates, for each of multiple rows of pixels in the image of the table, a probability of the row being a row separator, and a column prediction machine learning system generates, for each of multiple columns of pixels in the image of the table, a probability of the column being a column separator. An inference system uses these probabilities of the rows being row separators and the columns being column separators to identify the row separators and column separators for the table. These row separators and column separators are the layout of the table.

Abstract: Systems and techniques are described herein for directing a user conversation to obtain an editing query, and removing and replacing objects in an image based on the editing query. Pixels corresponding to an object in the image indicated by the editing query are ascertained. The editing query is processed to determine whether it includes a remove request or a replace request. A search query is constructed to obtain images, such as from a database of stock images, including fill material or replacement material to fulfill the remove request or replace request, respectively. Composite images are generated from the fill material or the replacement material and the image to be edited. Composite images are harmonized to remove editing artifacts and make the images look natural. A user interface exposes images, and the user interface accepts multi-modal user input during the directed user conversation.