Abstract: Systems and methods are disclosed for selecting target objects within digital images. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user indicators to select targeted objects in digital images. Specifically, the disclosed systems and methods can transform user indicators into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

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: 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 comprising drawing commands. The application generates an element proposal for each of many areas on a page of the input document tentatively identified as being page elements. Each of the element proposals may be generated at least in part based on the drawing commands. The page segmentation application classifies each of the element proposals into one of a plurality of defined type of categories of page elements at least in part based on the drawing commands. 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: Systems and methods are disclosed for selecting target objects within digital images. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user indicators to select targeted objects in digital images. Specifically, the disclosed systems and methods can transform user indicators into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

Abstract: A forecasting neural network receives data and extracts features from the data. A recurrent neural network included in the forecasting neural network provides forecasted features based on the extracted features. In an embodiment, the forecasting neural network receives an image, and features of the image are extracted. The recurrent neural network forecasts features based on the extracted features, and pose is forecasted based on the forecasted features. Additionally or alternatively, additional poses are forecasted based on additional forecasted features.

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 comprising drawing commands. The application generates an element proposal for each of many areas on a page of the input document tentatively identified as being page elements. Each of the element proposals may be generated at least in part based on the drawing commands. The page segmentation application classifies each of the element proposals into one of a plurality of defined type of categories of page elements at least in part based on the drawing commands. 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: A forecasting neural network receives data and extracts features from the data. A recurrent neural network included in the forecasting neural network provides forecasted features based on the extracted features. In an embodiment, the forecasting neural network receives an image, and features of the image are extracted. The recurrent neural network forecasts features based on the extracted features, and pose is forecasted based on the forecasted features. Additionally or alternatively, additional poses are forecasted based on additional forecasted features.

Abstract: A forecasting neural network receives data and extracts features from the data. A recurrent neural network included in the forecasting neural network provides forecasted features based on the extracted features. In an embodiment, the forecasting neural network receives an image, and features of the image are extracted. The recurrent neural network forecasts features based on the extracted features, and pose is forecasted based on the forecasted features. Additionally or alternatively, additional poses are forecasted based on additional forecasted features.

Abstract: Techniques for planar region-guided estimates of 3D geometry of objects depicted in a single 2D image. The techniques estimate regions of an image that are part of planar regions (i.e., flat surfaces) and use those planar region estimates to estimate the 3D geometry of the objects in the image. The planar regions and resulting 3D geometry are estimated using only a single 2D image of the objects. Training data from images of other objects is used to train a CNN with a model that is then used to make planar region estimates using a single 2D image. The planar region estimates, in one example, are based on estimates of planarity (surface plane information) and estimates of edges (depth discontinuities and edges between surface planes) that are estimated using models trained using images of other scenes.

Abstract: Provided are systems and techniques that provide an output phrase describing an image. An example method includes creating, with a convolutional neural network, feature maps describing image features in locations in the image. The method also includes providing a skeletal phrase for the image by processing the feature maps with a first long short-term memory (LSTM) neural network trained based on a first set of ground truth phrases which exclude attribute words. Then, attribute words are provided by processing the skeletal phrase and the feature maps with a second LSTM neural network trained based on a second set of ground truth phrases including words for attributes. Then, the method combines the skeletal phrase and the attribute words to form the output phrase.

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: Techniques for planar region-guided estimates of 3D geometry of objects depicted in a single 2D image. The techniques estimate regions of an image that are part of planar regions (i.e., flat surfaces) and use those planar region estimates to estimate the 3D geometry of the objects in the image. The planar regions and resulting 3D geometry are estimated using only a single 2D image of the objects. Training data from images of other objects is used to train a CNN with a model that is then used to make planar region estimates using a single 2D image. The planar region estimates, in one example, are based on estimates of planarity (surface plane information) and estimates of edges (depth discontinuities and edges between surface planes) that are estimated using models trained using images of other scenes.

Abstract: Certain aspects involve semantic segmentation of objects in a digital visual medium by determining a score for each pixel of the digital visual medium that is representative of a likelihood that each pixel corresponds to the objects associated with bounding boxes within the digital visual medium. An instance-level label that yields a label for each of the pixels of the digital visual medium corresponding to the objects is determined based, in part, on a collective probability map including the score for each pixel of the digital visual medium. In some aspects, the score for each pixel corresponding to each bounding box is determined by a prediction model trained by a neural network.

Abstract: A container (110) used for sterilization of medical components and utensils has a body (112) with a floor (114) and an upstanding wall (116). At least one vent (30), for entry of steam or the like, is formed in the floor. The vent has a plurality of vent holes, within a periphery defined by a ridge (34). A ledge (36) and a pair of raised portions (148) are provided inside the body to receive a rack on which the medical components are placed. A plurality of channels (144) in the floor of the body have a floor that is lower than the floor of the body, allowing gravity flow of liquid into the channels. The floor of each channel is adapted to enhance droplet formation, enhancing evaporation. The container is unitarily formed from a polymeric material selected for stability in the presence of high temperature and corrosive chemicals.

Abstract: Techniques for planar region-guided estimates of 3D geometry of objects depicted in a single 2D image. The techniques estimate regions of an image that are part of planar regions (i.e., flat surfaces) and use those planar region estimates to estimate the 3D geometry of the objects in the image. The planar regions and resulting 3D geometry are estimated using only a single 2D image of the objects. Training data from images of other objects is used to train a CNN with a model that is then used to make planar region estimates using a single 2D image. The planar region estimates, in one example, are based on estimates of planarity (surface plane information) and estimates of edges (depth discontinuities and edges between surface planes) that are estimated using models trained using images of other scenes.

Abstract: A container (10) used for sterilizing medical instruments and the like has a sealed filtered vent. A wall or a lid of the container has a vent area formed by a plurality of holes (12) that pass therethrough. The vent area is surrounded by a convex ridge (16) on an outside surface of the container, with a corresponding concave recess (26) on an opposing inside surface. A web of filter material (36) is sized and adapted to cover the vent area and overlie the concave recess. A cover plate (37) is generally planar, with a vent area formed by a plurality of holes (38) that pass through the cover plate. This vent area is surrounded by a convex ridge (43) that is sized and adapted to correspond to the concave recess of the sterilization container. An elastomeric gasket (127) with outwardly-projecting ridges is secured to at least the convex ridge of the cover plate.

Abstract: A personal inhalation device includes an outer shell having an orifice formed therein and containing a medium having one or more deliverables and an atomizing unit disposed within the shell. The atomizing unit atomizes the medium when a user puffs on the orifice such that vapor containing the deliverables is discharged through the orifice. The personal inhalation device is further capable of metering the deliverables discharged with the vapor.

Abstract: Systems and methods are disclosed for selecting target objects within digital images. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user indicators to select targeted objects in digital images. Specifically, the disclosed systems and methods can transform user indicators into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

Abstract: Systems and methods are disclosed herein for using one or more computing devices to automatically segment an object in an image by referencing a dataset of already-segmented images. The technique generally involves identifying a patch of an already-segmented image in the dataset based on the patch of the already-segmented image being similar to an area of the image including a patch of the image. The technique further involves identifying a mask of the patch of the already-segmented image, the mask representing a segmentation in the already-segmented image. The technique also involves segmenting the object in the image based on at least a portion of the mask of the patch of the already-segmented image.

Abstract: Systems and methods for efficiently absorbing, archiving, and distributing any size data sets are provided. Some embodiments provide flexible, policy-based distribution of high volume data through real time streaming as well as past data replay. In addition, some embodiments provide for a foundation of solid and unambiguous consistency across any vendor system through advanced version features. This consistency is particularly valuable to the financial industry, but also extremely useful to any company that manages multiple data distribution points for improved and reliable data availability.